OpenHuman: baixar versions anteriors

The Installed-Build Reliability Upgrade
This release focuses on keeping installed apps rock-solid—especially when loading key modules like search and memory. Onward and upward! 🎉
Highlights
Modules & installed builds 🧩
A targeted hotfix improves module admission in installed builds so critical modules load correctly again—unblocking both search (tinysearch) and memory (tinymemory) where they could previously fail due to module directory permission checks.
(#7155) — Thank you @senamakel!
Contributor Credits
Thanks to @senamakel for the fix and the fast turnaround!
Full Compare
https://github.com/tinyhumansai/openhuman/compare/v0.64.14...v0.64.15

The Files, Memory & Voice Power-Up
This release is a big step forward in day-to-day usability: clearer files and sessions, a major memory evolution, and real-time voice agents—plus a ton of reliability and performance work across the stack. 🎉
Highlights
Files & project workspace clarity 🗂️
Agent outputs now land in a visible Files folder, you can choose where that folder lives, and the app can surface those generated files directly in-place—making it much easier to find and use what your agent created. Large tool outputs are also handled more safely to keep projects tidy. (#6820, #6825, #6833, #6868, #6947) — Thank you @M3gA-Mind and @senamakel!
Memory v2, imports, and safer organization 🧠
Memory gets a major upgrade: engine-selectable memory v2, better lifecycle handling around each turn, and stronger portability when switching engines. The Memory UI and provider cards were modernized (including CortexDB), credits/free-period behavior is more consistent (with top-up prompts), and recall becomes time-zone aware.
Imports and migrations are significantly hardened: clearer “building vs empty” states, smarter batching/retries, better failure visibility with retry controls, more reliable resuming, and improved document ingestion (PDF/Office). Organization also improves with connector-first filing, better GitHub scoping, optional attribution to senders, and multiple erasure/deletion correctness and privacy/security fixes. (#6841, #6843, #6855, #6869, #6873, #6874, #6875, #6892, #6901, #6924, #6949, #6993, #7011, #7012, #7013, #7014, #7034, #7029, #7035, #7036, #7038, #7041, #7043, #7063, #7085, #7089, #7090, #7091, #7094, #7096, #7100, #7102, #7103, #7104, #7105, #7106, #7107, #7108, #7109, #7110, #7111, #7112, #7113, #7114, #7122, #7123, #7126, #7128, #7129, #7130, #7131, #7134, #7137, #7138, #7139, #7142, #7143, #7144, #7146, #7147, #7149) — Thank you @M3gA-Mind, @senamakel, @CodeGhost21, @YellowSnnowmann, and @lorenzozanee!
Live voice agents & voice foundations 🎙️
Voice agents are now truly live: talk to Tiny in real time with tool support (including Gemini Live, ElevenLabs, and Sarvam), plus a redesigned Voice agents experience with service cards, settings modals, and app-wide toasts. Under the hood, voice-related inference components were also reorganized for a cleaner foundation. (#7046, #7092, #6840) — Thank you @senamakel!
Chat UX upgrades & smoother conversation control 💬
Chat gets a substantial UI uplift: working folder support, per-model thinking controls, real thread titles, richer sidebar context, and clearer run-state cues. Reliability improves too—Stop is more resilient, streaming works even without a progress sink, reply-language directives are consistently sent, and several web chat delivery edge cases are fixed. The app also adds translatable error copy and improves transcript storage formats. (#7048, #7045, #6916, #7088, #7097, #7098, #6844, #7087, #6881, #6883) — Thank you @senamakel and @M3gA-Mind!
Agent intelligence, tool governance, and turn reliability 🧰
Agents are more robust and predictable: improved tool calling defaults (JSON auto) with a setting, better “finish” verification, fewer false failure classifications, clearer file-read behavior, and multiple fixes around context compaction, reasoning bounds, iteration caps, and hosted-path correctness/telemetry. Tool policy/approval gates were reworked, per-turn tool withholding was added, and timed-out commands now terminate their whole process group.
This also includes targeted fixes for web research budgets, credential scrubber behavior (including avoiding code redaction), handling HTTP status correctly, and improved orchestration behaviors. (#6910, #6909, #6963, #6965, #6966, #6967, #6968, #6969, #6971, #6972, #6973, #6974, #6975, #6976, #6977, #6980, #6992, #6889, #6856, #6879, #6884, #6945, #6946, #7117, #7118, #7119, #7120, #7140, #6865) — Thank you @senamakel and @sanil-23!
Sessions, scheduling, connectors & integrations 🧩
A new host-injected se

The Speed, Structure & Reliability Upgrade
This release tightens the core experience from end to end—faster first turns, clearer chat feedback, sturdier integrations, and a big internal modularity push that sets us up for even quicker iteration. 🎉
Highlights
Performance & responsiveness ⚡
The agent loop is noticeably snappier: first-turn prompts are dramatically smaller, prompt caching stays warm (improving time-to-first-token), and the managed inference path avoids unnecessary per-call client setup. Tool-output compaction is also enabled by default again—with new “REPL-style” tools over stored results to keep large tool outputs from stalling turns.
(#6787, #6788, #6823) — Thank you @senamakel!
Chat UI & approvals polish 💬
Chat got a round of UX improvements: long source lists now collapse cleanly (with better favicons), web-search rendering no longer leaves awkward gaps, and the silence watchdog now warns instead of killing a running turn—staying in sync with the core’s actual turn state. Approvals are also smoother: answered approvals won’t “ghost” into the background deck, and refusals now carry a clear deny reason that the model can actually read.
(#6802, #6827, #6800, #6810) — Thank you @senamakel and @M3gA-Mind!
Memory & knowledge engines 🧠
Memory is now explicitly selectable: you can choose exactly one active engine, including Local (TinyCortex) or CortexDB via TinyHumans, plus other supported providers. Switching engines can also copy existing memories across—making experimentation and migration much less painful.
(#6777) — Thank you @senamakel!
MCP & Composio integrations 🔌
MCP tooling becomes much more ergonomic and robust: server tools are exposed as stable, individually-addressable tools from a persistent cache, and string-encoded JSON arguments are normalized so calls don’t fail unexpectedly. Refusals from tool listing now tell the model what it can do (and avoid pointing at RPC-only methods). On the Composio side, embedders can give each agent its own credentials, and backend-routed Composio calls now flow through the tinyconnectors module instead of an in-process client.
(#6767, #6769, #6818, #6689, #6796) — Thank you @senamakel, @M3gA-Mind, and @oxoxDev!
Security, safety & policy hardening 🛡️
Security protections are sharper and less noisy: the prompt-injection guard is less likely to false-positive on recalled transcripts, and browser IP blocking now uses the full non-global range definitions (with regression tests). Shell execution reliability also improves in scheduled jobs on Windows, and shell scanning logic is consolidated upstream for consistency.
(#6776, #6709, #6764, #6790) — Thank you @senamakel, @Avi-Bendetsky, and @sanil-23!
Architecture & vendor modularity push 🧱
A major theme of this series is extracting host-independent logic out of openhuman-core and into the appropriate vendor/tiny* modules—keeping core focused on product policy, adapters, and contracts. This includes splitting RPC/server responsibilities, moving channels/skills/web3/filesystem/hooks/session/runtime/tooling helpers into their owning crates, and updating vendor pins to merged upstream mains. Along the way, stale subsystem references were cleaned up, and the tool-call type is now adopted directly from tinytools to reduce duplication and drift.
(#6703, #6779, #6780, #6782, #6783, #6784, #6785, #6786, #6789, #6791, #6793, #6794, #6795, #6797, #6804, #6805, #6806, #6807, #6809, #6773) — Thank you @senamakel!
Reliability, updates & CI/e2e stability ✅
This set also focuses on “keeping main green”: E2E web runs now avoid port collisions and refuse taken ports, the core updater once again resolves the correct versioned archive and stages the real binary, and managed backend outages now trigger bounded exponential backoff with explicit terminal outcomes. CI coverage improves too, including executing module-gated Rust tests, better layout gating behavior, and keeping vendor/lockfile pins aligned (including tinymcp and tinymemory pin

The Intelligence Upgrade 🎉
v0.64.4 to v0.64.7 brings 12 PRs across 12 commits, with upgrades across memory, voice, agents, reliability, and developer foundations. Thank you to everyone who contributed to this release. ✨
Highlights 🚀
✅ Tasks, chat & agent workflows
Task, chat, and agent workflows become easier to steer and inspect, with better task boards, persistent run state, safer delegation, and clearer model/thread controls. (#6672, #6683, #6702, #6760) — Thank you @M3gA-Mind and @senamakel!
🧩 Integrations, UI & developer foundations
Integrations, UI polish, and developer foundations also move forward, including clearer connected-account surfaces, meeting-agent wiring, presentation/artifact improvements, and cleaner docs/code organization. (#6668, #6678, #6693, #6699, #6700, #6701, #6704, #6759) — Thank you @senamakel, @M3gA-Mind, and @siddarthkay!
Contributor Credits 🙌
- M3gA-Mind (#6672, #6693) — thank you!
- senamakel (#6668, #6678, #6683, #6700, #6701, #6702, #6704, #6759, #6760) — thank you!
- siddarthkay (#6699) — thank you!
Full Compare 🧭
https://github.com/tinyhumansai/openhuman/compare/v0.64.4...v0.64.7

The Better Windows Desktop Upgrade
This release is all about making the Windows desktop experience more reliable, more polished, and smoother to operate—especially when you’re offline. 🎉
Highlights
Offline-ready Windows installers 📦
Windows desktop installers now bundle all registry-pinned native modules (and their extracted DLLs) directly into the installer, so key features don’t depend on a first-run download. Module resolution now prefers the read-only installer bundle before user cache or network, and the Windows checks/smoke steps were updated to verify offline module loading end-to-end. (#6687) — Thank you @senamakel!
Sharper Windows window controls & cleaner shutdown 🪟
Windows gets a more compact first-launch window and improved custom window controls (minimize, maximize/restore, close), with the drag strip staying available during boot and error screens. Shutdown behavior is also fixed so closing properly exits both the desktop host and embedded core (including support for the app_quit IPC command), plus the dev launcher was simplified with earlier architecture mismatch detection. (#6692) — Thank you @stevent95-star!
Contributor Credits
Thanks to everyone who contributed to this release: @senamakel, @stevent95-star.
Full Compare
https://github.com/tinyhumansai/openhuman/compare/v0.64.3...v0.64.4

The Smooth Release Bump Upgrade
v0.63.12 is here—a clean, streamlined release update to keep everything moving forward. 🎉
Highlights
Release automation & housekeeping ⚙️
This update is focused on release hygiene: bumping the version to v0.63.12 via the automated release workflow, with no feature or bugfix PRs included in this range. — Thank you @github-actions[bot]!
Contributor Credits
Thanks to @github-actions[bot] for shipping this release update.
Full Compare
https://github.com/tinyhumansai/openhuman/compare/v0.63.11...v0.63.12

OpenHuman v0.63.11
187 commits — 52 features, 90 fixes, 45 refactors, docs and CI. This release carries everything merged to main since v0.63.9, including the kernel restructure, ElevenLabs Voice Agents, and a large reliability pass across memory, inference and voice.
Note on the previous notes: an earlier version of this page listed only the two release-promotion PRs. That was an artefact of how release is updated, not a description of the release. The full contents are below.
Highlights
Voice
- ElevenLabs Voice Agents — core RPC, realtime session, and local-agent relay handler (#5407)
- Send the relay identity token where the backend can read it (#5428)
- Stop the Piper voice id leaking into non-Piper TTS providers (#5367)
- Repair the execute bit on extracted Piper binaries (#5216), handle U16 sample format in the fallback capture path (#4537)
Memory & embeddings
- Warn before the embedding budget silently stops memory (#5402)
- Stop a signed-in user's embeddings failing, and unstick the parked queue (#5427)
- Classify Ollama-unavailable embed failures actionably (#5398)
- Drain the coding-session backlog across bounded passes (#5368)
- Canonicalize memory identifiers symmetrically (#5275); stop paging on caller ingest-payload schema errors (#5280)
Inference & model routing
- Route Codex OAuth chat to the subscription backend (#5371)
- Error on a misconfigured vision model instead of substituting (#5262); route vision at vision-capable models (#5253)
- Explain background-role provider fallback and verify BYOK keys (#5254)
- Route local AI through TinyAgents RPC (#5240); local model reliability — /api/tags fallback and real Ollama model ids (#5219)
Flows
- Surface bounded loops from the tinyflows engine (#5366)
- Accept declared workflow inputs on every run path (#5304)
- Per-item fan-out — run an array of flow work concurrently (#5302)
- Canvas visual refresh — kind tiles, elevation, step numbers (#5303)
Agent & chat
- Send user image attachments as image blocks, not text (#5370)
- Preserve chat context across a Quick/Reasoning switch (#5401)
- Name a thread in three words (#5412)
- Name the chat-template rejection instead of blaming model/temperature (#5309)
- Filesystem-offload convention for worker artifacts on long-horizon tasks (#5217)
Kernel restructure
- Collapse 124 flat domains into 31 gate-aligned families (#5328) — pure moves, byte-identical wire surface
- Kernelize openhuman: cut the workflow dependency floor 418 → 280 crates (#5314)
- Realign DomainGroup with the family directories (#5332) and guard three unenforced consumers (#5364)
- Gate the macOS Contacts cohort behind contacts (#5365); host capability adapters and config seam (#5396)
Media, mascot & config
- Error instead of false success on the generation poll timeout (#5411)
- Accept PNG/GIF/JPEG/WebP custom avatars with file upload (#5420)
- Surface a user notice when a corrupt config.toml is reset (#5340); stop transient active_user.toml read faults from resetting the profile (#5337)
Channels & sessions
- Stop a missing edit route from looking like a deleted message (#5283)
- Keep the /auth/me 401 classifiable as session expiry rather than a hard logout (#5311)
- Stop out-of-credits background scouts paging Sentry (#5310)
Contributors
Thank you to everyone who shipped this release:

| Contributor | Commits |
| ------------------- | ------- |
| Steven Enamakel | 50 |
| Cyrus Gray | 45 |
| Mega Mind | 31 |
| YellowSnnowmann | 28 |
| mysma-9403 | 6 |
| CodeGhost21 | 6 |
| Sam | 3 |
| github-actions[bot] | 7 |

Full compare
https://github.com/tinyhumansai/openhuman/compare/v0.63.9...v0.63.11

The Release-Reliability Upgrade
This set of releases tightens up the shipping pipeline and keeps the release branch moving smoothly—so builds stay green and delivery stays fast. 🎉
Highlights
Release branch sync & conflict resolution 🔀
We kept release in lockstep with main through a series of promotions, ensuring the latest accumulated work lands cleanly where production builds are cut.
One promotion also required a careful conflict resolution pass to preserve the already-cut release versions while still bringing forward the full set of changes from main. (#5203, #5242, #5256) — Thank you @M3gA-Mind!
Linux AppImage release unblock 🐧
Linux desktop release smoke tests are back on track: an AppImage startup failure on Ubuntu 23.10+ was addressed by adjusting the user namespace sysctl behavior used during the release job, unblocking production runs. (#5251) — Thank you @M3gA-Mind!
Contributor Credits
Thank you to everyone who contributed to this release: @M3gA-Mind, @github-actions[bot].
Full Compare
https://github.com/tinyhumansai/openhuman/compare/v0.63.1...v0.63.9

The Composio Reliability Upgrade
This patch release tightens up Composio task execution and makes tool-calls more resilient, so your agents can get to work faster and recover more gracefully when model output gets messy. 🚀
Highlights
Composio task execution & schema validation 🧩
Composio actions triggered via integrations_agent now avoid a frustrating “first call bounce” and can execute immediately when the model’s arguments already match the resolved live contract. This prevents loops like “fetch my latest email” stalling before GMAIL_FETCH_EMAILS ever runs, especially along the text-mode per-action path. (#5132) — Thank you @M3gA-Mind!
Tool-call parsing robustness (Kimi recovery) 🛠️
Tool-call parsing has been hardened to better recover from Kimi-K2-family garbled tool-call bodies. The normalization now strips the <|\"|> argument-quote sentinels and rewrites malformed NAME{unquoted-json} into a canonical form, improving resilience when model output is slightly corrupted. (#5132) — Thank you @M3gA-Mind!
Contributor Credits
Thanks to everyone who contributed to v0.63.1: @M3gA-Mind and @github-actions[bot].
Full Compare
https://github.com/tinyhumansai/openhuman/compare/v0.63.0...v0.63.1

The Reliability & Control Upgrade
This release is packed with sturdier workflows, smoother chat and Agent World experiences, and a ton of under-the-hood hardening to keep everything fast and dependable. 🎉
Highlights
Workflows you can trust 🧩
The Workflows copilot and canvas got a major reliability pass: proposals consistently render (even for larger graphs), every copilot turn now ends in a real terminal outcome (no more silent trail‑offs), Accept now saves automatically, and the runs UI stays accurate and live-updating. Safety and correctness also improved with fixes for live-arming on updates, better circuit-breaking, approval-state visibility, and stronger tier/approval enforcement for Composio tool calls.
(#4881, #4886, #4887, #4888, #4889, #4890, #4891, #4893, #4904, #4911, #4932, #4933, #4941, #4942, #4943, #4945, #4955, #4956, #4999, #5000, #5007, #5011, #5012, #5013) — Thank you @graycyrus and @senamakel!
Chat that feels snappier & more controllable 💬
Chat got a big UX win with a Stop button plus ESC-to-interrupt and re-edit, and stronger protection against “hydrate” snapshots wiping fresh streaming or tool timelines. Orchestration also became more transparent: async sub-agent failures and “awaiting user” outcomes now surface correctly in chat, and delegations are now async-by-default with durable, resumable sessions and persistent workflow proposals.
(#4898, #4903, #4908, #5074) — Thank you @M3gA-Mind, @graycyrus, and @senamakel!
Memory & transcript upgrades 🧠
Memory ingestion and recall got sharper and safer: OpenHuman can ingest Codex and Claude coding sessions, Composio sync no longer keys upserts off secret-like titles, and recall avoids pulling same-session “echo” documents that drown out real facts. On top of that, transcripts are now much more robust: cold-boot resumes restore full-fidelity context and thinking, and the transcript system is moving to an append-only, derived view with raw session logs as the source of truth.
(#4863, #4953, #4991, #5077, #5086) — Thank you @senamakel, @M3gA-Mind, and @graycyrus!
Agent World (Tiny Place) feels alive 🌍
Tiny Place is now more interactive and complete: DMs and feeds update in real time, ledgers and feeds paginate beyond the first 50 items, and directory entries finally open a rich profile view. Profiles also leveled up with editing for your own profile (name/bio/avatar) and a public viewer route for arbitrary handles.
(#4951, #4952, #4988, #4989, #4990, #4994, #4996, #4997) — Thank you @M3gA-Mind!
Performance, polish, and “it just works” fixes ⚡
From accessibility and UI polish to startup and runtime performance, this release reduces friction across the app: improved dark theme contrast, paused mesh-gradient rendering when the app isn’t visible, and boot polling is consolidated and quieter. First-run setup overlays now appear only when actually provisioning, channel setup guidance is corrected in-app, pricing/checkout redirects behave properly, and the settings “Clear App Data” reset now correctly targets the signed-in user.
(#4897, #4902, #4905, #4910, #4939, #4954, #5035, #5036, #5066, #5075, #5085) — Thank you @M3gA-Mind, @YellowSnnowmann, and @senamakel!
Build flexibility, CI hardening, and new surfaces 🛠️
The core is now far more modular and easier to ship in slim builds via compile-time feature gates (media, web3, flows, skills, MCP, meet) and a new feature-gated terminal chat UI (openhuman tui). Desktop shipping and CI also got stricter and safer: voice and tokenjuice-treesitter are correctly forwarded into the desktop build, CI now gates feature-forwarding drift, macOS clippy blockers are resolved, the “gates-off” smoke lane is repaired and runs tests, and learning startup subscribers are decoupled from channels and covered with more stable tests. There’s also a core refactor moving the web chat conduit out of channels/.
(#4840, #4855, #4912, #4913, #4914, #4915, #4916, #4917, #4934, #5004, #5020, #5023, #5025, #5070, #5082, #5084) — Thank you @oxoxDev,

The Smooth Shipping Upgrade
v0.61.2 → v0.61.8 is all about clean release momentum—promoting the latest work from main into release so staging/prod builds can pick up the newest improvements. Onward and upward. 🚀
Highlights
Release pipeline & promotion 🚢
This release primarily reflects a clean promotion of main into release, bringing the accumulated changes forward with a fast-forwardable merge (no divergence), ready for staging and production cuts.
(#4936) — Thank you @M3gA-Mind!
Contributor Credits
Thanks to everyone who contributed to this release: @M3gA-Mind, @github-actions[bot].
Full Compare
https://github.com/tinyhumansai/openhuman/compare/v0.61.2...v0.61.8

The Meetings & Connections Power‑Up
v0.58.0–v0.58.7 is packed with a sharper Meetings experience, faster + more reliable Connections (Skills/MCP), and a big wave of stability upgrades across agents, memory, and providers. 🚀
Highlights
Meetings, end-to-end polish 🎥
Meetings got a full redesign with a platform selector, a clean history master-detail layout, and smarter defaults—plus a bunch of quality fixes that make sessions feel more “alive” and less error-prone. You’ll see better UI feedback (including “Leaving…” states), automatic refresh of Recent Calls when a meeting ends, and improved handling of backend capacity messaging.
Wake phrases are now correctly forwarded for active meeting bots, meeting display names can auto-fill from your connected account, and the auto-summarize policy is honored—with a new manual summary RPC for “Ask” flows.
(#4308, #4348, #4347, #4221, #4231, #4297, #4353) — Thank you @graycyrus and @YOMXXX!
Connections: MCP & Skills that feel fast (and stay fast) 🔌
MCP took a major leap forward: the MCP Servers page is now “complete” with a curated catalog, lifecycle improvements, and E2E coverage. Under the hood, MCP tool calls return as soon as the reply frame arrives (huge latency win), stdio servers spawn with the user’s real shell PATH (hello npx/uvx), and schema migrations are now concurrency-safe.
Auth and install UX also improved across the board: clearer MCP 401 explanations (with safer messaging), better “installed / installing” card state, and Skills improvements like activation persistence, registry caching + pagination, and latency instrumentation.
(#4300, #4220, #4295, #4219, #4321, #4224, #4288, #4120, #4182, #4188, #4238) — Thank you @YellowSnnowmann, @M3gA-Mind, @oxoxDev, and @YOMXXX!
Chat experience: attachments, visuals, and smoother long turns 💬
Chat now has a first-class attachment button for images, videos, and documents—with drag-and-drop and paste support. Code blocks gained syntax highlighting across markdown surfaces, and the composer/footer layout now dynamically reserves space so queued follow-ups (and other expanding footer content) no longer overlap the conversation.
On the reliability side, long reasoning turns stay alive past the old 2-minute silence timeout thanks to a heartbeat progress signal.
(#4292, #4335, #4334, #4282) — Thank you @oxoxDev and @graycyrus!
Agents & tool runtime: fewer loops, clearer stops 🧠
Agent orchestration is now much harder to derail: identical tool-call loops are detected and halted, stuck sub-agents can return as explicitly incomplete, and session tool calls now respect timeouts instead of hanging forever. The MCP Setup Agent no longer gets trapped in a re-spawn loop when pausing for user clarification, and goal completion instructions were strengthened to improve auto-complete behavior.
The built-in researcher agent was also tightened up with a bounded tool surface and capped per-turn output.
(#4230, #4262, #4303, #4310, #4313, #4314) — Thank you @sanil-23, @YOMXXX, @oxoxDev, @salarkhannn, and @senamakel!
Memory & intelligence: better continuity and safer cross-host behavior 🗂️
Memory got meaningful durability upgrades: summary-only wiki history is now tracked via git, cross-thread search is faster by ranking before cloning heavy hits, and the Trees UI has clearer feedback and a stable toolbar layout even when vault guidance opens.
For multi-device setups, cross-host vault paths are now explicitly surfaced as belonging to a particular host OS—so a frontend won’t try to open macOS paths on Linux (or vice versa). The Brain memory graph reliably reloads after re-login, and the Intelligence page scrolls correctly inside the Brain card.
(#4168, #4311, #4331, #4342, #4330, #4223, #4332) — Thank you @senamakel, @mysma-9403, @graycyrus, @oxoxDev, and @M3gA-Mind!
Provider, inference, and observability hardening 🧰
This release includes a broad set of fixes that turn noisy “errors” into correctly-classified expected states, reduce retry storms, and 

Super Context is Here! 🎉
v0.57.53 to v0.58.0 brings 124 PRs across 133 commits, with upgrades across memory, voice, agents, reliability, and developer foundations. Thank you to everyone who contributed to this release. ✨
Highlights 🚀
🧠 Memory & intelligence
Memory and intelligence flows are faster, clearer, and more resilient, from source sync controls and richer ingest to batched embeddings and delegated memory retrieval. (#3947, #3948, #3949, #3951, #3959, #3960, #3999, #4008, #4049, #4051, #4054, #4063, #4066, #4067, #4070, #4083, #4086, #4087, #4100, #4106, #4107, #4133, #4138) — Thank you @senamakel, @M3gA-Mind, @oxoxDev, @graycyrus, @mysma-9403, @Subharup-31, @sanil-23, and @senamakel-droid!
✅ Tasks, chat & agent workflows
Task, chat, and agent workflows become easier to steer and inspect, with better task boards, persistent run state, safer delegation, and clearer model/thread controls. (#3918, #3925, #3933, #3965, #3966, #3970, #3977, #3978, #3983, #3985, #3987, #3990, #3994, #4003, #4007, #4011, #4012, #4016, #4017, #4018, #4019, #4021, #4027, #4030, #4031, #4050, #4060, #4061, #4062, #4080, #4081, #4082, #4084, #4085, #4102, #4103, #4105, #4114, #4128, #4129, #4130, #4132, #4134, #4136, #4139, #4141, #4156, #4173) — Thank you @Felyx-Fu, @graycyrus, @sanil-23, @M3gA-Mind, @nazarli-shabnam, @ly-wang19, @YellowSnnowmann, @oxoxDev, @senamakel, @hgunduzoglu, and @senamakel-droid!
🔐 Reliability, security & platform polish
Reliability and platform behavior are tightened across security policy, credential handling, session health, CEF startup, Windows filesystem edge cases, and release-only build paths. (#3958, #3969, #3974, #3976, #3992, #4004, #4009, #4028, #4058, #4064, #4065, #4068, #4069, #4076, #4078, #4101) — Thank you @M3gA-Mind, @oxoxDev, and @senamakel!
🧩 Integrations, UI & developer foundations
Integrations, UI polish, and developer foundations also move forward, including clearer connected-account surfaces, meeting-agent wiring, presentation/artifact improvements, and cleaner docs/code organization. (#3718, #3941, #3946, #3973, #3975, #3981, #3982, #3984, #3986, #3988, #3989, #3995, #3998, #4002, #4026, #4032, #4037, #4052, #4053, #4057, #4071, #4072, #4079, #4108, #4109, #4110, #4113, #4115, #4123, #4124, #4125, #4126, #4127, #4131, #4137, #4162, #4171) — Thank you @obchain, @martian56, @M3gA-Mind, @nazarli-shabnam, @graycyrus, @senamakel, @oxoxDev, @sanil-23, @YellowSnnowmann, and @senamakel-droid!
New Contributors 🌟
- Welcome Martian! Thank you for #3941 fix(composio): pin toolkit_versions=latest in direct-mode tool listings (#3932); #3946 fix(tauri): identify foreign process on core port + consent-gated force-quit (#3331).
- Welcome Shabnam! Thank you for #3970 fix(sentry): re-register inboundFiltersIntegration so ignoreErrors runs; #3984 fix(settings): render Managed provider as always-on badge, not a locked toggle.
Hope you join the Discord for exclusive roles and contributor rewards!
Contributor Credits 🙌
- Cyrus Gray (#3925, #3990, #3994, #3995, #3998, #4002, #4007, #4008, #4018, #4019, #4037, #4052, #4053, #4054, #4057, #4103, #4109, #4110, #4156, #4162) — thank you!
- Felix (#3918, #4012) — thank you!
- github-actions[bot] — thank you!
- Hüsam (#4050) — thank you!
- ly-wang19 (#3978) — thank you!
- Martian (#3941, #3946) — thank you!
- Mega Mind (#3951, #3958, #3959, #3960, #3965, #3966, #3973, #3975, #3977, #3981, #3982, #3983, #3985, #3986, #4064, #4065, #4066, #4067, #4068, #4069, #4070, #4071, #4078, #4171) — thank you!
- mysma-9403 (#4049, #4063) — thank you!
- obchain (#3718, #3988, #3989) — thank you!
- oxoxDev (#3969, #3974, #3976, #3992, #3999, #4003, #4004, #4009, #4011, #4030, #4031, #4032, #4058, #4060, #4061, #4072, #4076, #4101, #4102, #4108, #4114, #4115, #4127) — thank you!
- sanil-23 (#3933, #4016, #4079, #4080, #4082, #4083, #4128) — thank you!
- Shabnam (#3970, #3984) — thank you!
- Steven Enamakel (#3947, #3948, #3949, #4017, #4021, #4026, #4027, #4028, #4081, #4084, #4085, #4

The Stability & Flow Upgrade
This release is packed with quality-of-life polish and reliability fixes across chat, voice, auth, and integrations—plus a few big building blocks for the agent runtime. Enjoy the smoother ride 🎉
Highlights
Chat experience & UI polish ✨
Chat gets a noticeably cleaner feel: scheduled morning briefings now stay grouped (headings + bodies in the same bubble), approval prompts are easier to read with an opaque warning surface, and GFM markdown tables render correctly in agent output. We also fixed edge-case UI issues like the sidebar composer footer being reachable even on short windows, and improved attachment fallback parsing so FILE markers don’t leak into reconstructed messages.
(#3851, #3790, #3857, #3863, #3795) — Thank you @sanil-23, @discolotus, @YOMXXX, @hgunduzoglu, and @rsd-darshan!
Voice & audio reliability 🎙️
Voice setup and hands-free flows are sturdier: push-to-talk commands are properly allowlisted again, local Whisper/Piper providers can’t be enabled until installation is truly complete (with polling + better progress states), and lapsed-session TTS 401s are now correctly treated as session expiry instead of noisy hard errors.
(#3842, #3861, #3750) — Thank you @oxoxDev and @YOMXXX!
Auth, sessions, and fewer dead-ends 🔐
Sign-in and session handling got smarter: transient /auth/me hiccups no longer prevent session persistence, legacy /auth web callbacks are accepted and rewritten safely for HashRouter, and OpenRouter OAuth now uses the loopback listener’s actual bound port (fixing the “port 3000 busy” case). Multiple 401 paths (integrations + voice) now drive the user into a clean re-login flow instead of failing silently.
(#3746, #3800, #3904, #3749) — Thank you @samrusani, @NgoQuocViet2001, @ly-wang19, and @oxoxDev!
Providers, inference & routing upgrades ⚡
A bunch of provider-facing improvements landed: OpenAI-compatible HTTP timeouts are now configurable (so long reasoning turns don’t get chopped), Gemini tool-call history correctly preserves thought_signature, and user-misconfig errors like /models 404s now get classified at the source with actionable hints. We also added new provider options—ModelScope as a built-in hosted provider, and OMLX as a named local provider with endpoint+key credentials.
(#3864, #3770, #3769, #3773, #3862) — Thank you @hgunduzoglu, @oxoxDev, @yrk111222, and @hliebscher!
Agents: orchestration, subagents, and context headroom 🤖
The agent runtime got major upgrades: an event-driven subconscious trigger pipeline introduces a long-lived orchestrator session, tool-output compaction reduces context bloat (with reversible recovery), and subagents are now async + reusable by default (with lifecycle tools). We also improved failure behavior—agent cascades now stop on the first permanent inference failure with a clearer root cause, and local-context overflow errors are caught pre-dispatch with concrete guidance.
(#3650, #3869, #3887, #3779, #3771) — Thank you @senamakel, @sanil-23, and @oxoxDev!
Memory & sync performance (and correctness) 🧠
Memory got both faster and more correct: semantic recall is query-sensitive again, episodic relevance avoids an O(n²) hot path, and chunk scoring dedup now uses cheaper HashSets. The memory tree sealing path is more concurrent, and source sync (GitHub) and calendar fan-out use bounded concurrency for better throughput. On the sync side, Composio incremental sync is now centralized behind a generic orchestrator (with providers migrated across Notion/GitHub/Linear/ClickUp/Gmail/Slack and cap math moved into a single source of truth).
(#3608, #3782, #3638, #3416, #3434, #3472, #3852, #3860, #3873, #3874, #3924, #3937) — Thank you @michaelk1957, @mysma-9403, and @sanil-23!
Skills, toolchains, and Windows/Linux shell quality 🧰
Skills management is sharper: uninstalling a skill mid-session now retracts it from the live catalog, built-in catalog entries correctly show as Installed, and community skill downloads now resolve via eac

The Agent World & Wallet Safety Upgrade
This release brings a big leap in Agent World depth, smoother navigation across the app, and a major wallet-safety fix—plus quality-of-life polish throughout. 🎉
Highlights
Agent World goes native 🌍
Agent World (tiny.place) is now deeply integrated with a full Rust data layer and a ported React UI, unlocking core surfaces like Feed, Messages, Jobs/Bounties, Directory/Identities, and devnet payment flows with confirm-before-spend. On top of that foundation, Explore now pulls real live data, identity registration publishes to the Directory correctly, DMs resolve handles reliably, and groups/creating bounties give clearer UX feedback.
(#3780, #3839, #3847, #3846, #3840, #3837, #3835) — Thank you @graycyrus!
Smarter agent workflows & orchestration 🤖
Detached background sub-agents now cleanly cancel when their parent thread is closed, preventing “fire-and-forget” runs against deleted conversations. And the agent is now grounded to a live per-turn clock so time-relative statements (“good morning”, “today/tomorrow”) stay accurate across long sessions.
(#3742, #3752) — Thank you @sanil-23!
Wallet safety, visibility, and trust 🔐
A critical wallet fix ensures the Recovery Phrase experience reveals the existing phrase instead of accidentally regenerating/overwriting a user’s wallet—now guarded by an explicit “force” path and a clearer UI state machine. Wallet access is also more discoverable with a prominent sidebar entry, and Agent World now shows a handy wallet address chip in its sidebar header.
(#3849, #3836, #3838) — Thank you @graycyrus!
Navigation & chat shell polish 🧭
The shell is easier to use when collapsed thanks to an icon-only navigation rail that stays fully navigable, complete with tooltips and active state. The sidebar header is also cleaner (language picker moved to Settings), and the chat/sidebar experience gets a meaningful rework with thread-title rename flowing into the sidebar and other chat shell refinements.
(#3802, #3810, #3854) — Thank you @graycyrus and @senamakel!
Rewards + Discord linking made real 🎁
Discord linking now actually runs OAuth from the Rewards page (and returns you right back), and the Rewards experience adds disconnect/re-link plus clear per-achievement role assignment status—so claiming roles is transparent and actionable.
(#3748, #3766) — Thank you @YellowSnnowmann!
Localization & UX correctness fixes 🌐
More user-facing strings are now fully localized, including OpenHuman Link account/notification messaging and the Model Council hint picker labels—closing gaps where English literals bypassed i18n. Also, Conscious loop triggers are now guarded to prevent duplicate runs on rapid clicks.
(#3702, #3704, #3708) — Thank you @obchain!
Embedded webview providers expand 🧩
The embedded webview account picker now supports more mainstream providers—Gmail, Outlook, Instagram, and X—across frontend, Tauri shell, core login detection, and provider recipes.
(#3755) — Thank you @senamakel!
Test & release health improvements 🧪
E2E coverage and Playwright/Vitest setup were adapted to the chat-as-home shell, fixing navigation races and stabilizing coverage timeouts.
(#3754) — Thank you @senamakel!
Agent World UI alignment & sidebar cleanup 🧹
Agent World continues to be streamlined: Jobs is now hidden from the Agent World sidebar (while keeping the route accessible for deep links), and job applying gains an agent tool plus a clearer “proposal submitted” success UX.
(#3855, #3848) — Thank you @graycyrus!
Linux packaging reliability 🐧
AppImage bundling now consistently replaces the bundled ld-linux from the CI host system to prevent glibc mismatch crashes seen on newer distros (e.g., Fedora with glibc ≥ 2.42).
(#3645) — Thank you @0xhis!
New Contributors
- Thank you @0xhis for fixing AppImage glibc mismatch crashes by ensuring the bundled ld-linux is always replaced from the host system. (#3645)
Hope you’ll join our Discord—come grab your exclusive roles and contribu

The Orchestration & Everyday-Flow Upgrade
This release brings a big leap in how OpenHuman runs—from smarter multi-agent orchestration and skills, to a cleaner two-panel app shell, to faster and quieter memory + inference pipelines. 🚀
Highlights
Intelligence & multi-agent orchestration 🧠
OpenHuman’s “intelligence layer” gets much more real: async sub-agents can now be steered while running and awaited cleanly, teammate agents can actually execute tasks end-to-end (with messaging captured in timelines), and durable workflow orchestration now has a first-class UI with an approval gate for high-cost runs. Worktree isolation is also wired through RPC + UI so complex runs can stay contained and observable.
(#3641, #3637, #3697, #3696) — Thank you @senamakel and @oxoxDev!
Skills, vision, and better agent grounding 🧰
Skills graduate to a catalog-driven run_skill flow with an isolated executor and mid-session refresh—making skill runs more reliable and less invasive to chat history. There’s also a new vision-v1 tier plus a dedicated vision sub-agent for image understanding, and tighter numeric grounding rules to keep numbers copied exactly from observed sources.
(#3722, #3699, #3678) — Thank you @sanil-23 and @Sam!
Chat & background work UX polish 💬
Detached sub-agents now have a proper “Background tasks” panel and deliver results back into chat in an idle-gated, batched way—so you don’t get interrupted mid-turn. Conversations also get a key rendering fix: task insights now appear once, after the full response. Plus, proactive messages are now limited to fresh threads, and resume-on-reopen errors are classified and threads are “de-poisoned” to recover cleanly.
(#3735, #3726, #3713, #3714) — Thank you @sanil-23!
A new two-panel desktop shell & settings experience 🧭
The desktop app’s layout continues its transformation: TwoPanelLayout becomes the backbone across Settings/Brain/Connections/Chat, settings panels are unified with shared primitives for consistent navigation, and the root shell now adopts a unified sidebar with Chat as the home experience. There’s also a dedicated Desktop Agent setup panel to make permissions, seamless mode, always-on, and wake-word setup feel centralized and clear.
(#3643, #3646, #3751, #3634) — Thank you @senamakel and @M3gA-Mind!
MCP, connectors, and provider setup—faster and more actionable 🔌
MCP servers are now usable end-to-end by the agent (including OAuth flows and an agent bridge), boot is faster thanks to concurrent server spawning, and 401s are surfaced as an actionable “needs sign-in” state. Claude Code becomes an opt-in provider with a macOS auth fix and OpenHuman memory over MCP, and Composio/memory-source reconciliation is significantly more efficient. A small but helpful settings addition also adds a “Get API key” link for Kimi.
(#3648, #3429, #3719, #3647, #3432, #3685) — Thank you @sanil-23, @mysma-9403, and @Huyuochi!
Memory & retrieval that feels more “right” 🧠
Memory status reporting is smarter (only unrecoverable failures show as “error,” and the degraded latch clears on any completed extraction). There’s a new RPC to fully delete a memory source by exact source_id, and a new cover_window retrieval mode that powers a more relevant “last 24h” morning brief. Under the hood, extraction scoring avoids unnecessary cloning for lower overhead.
(#3630, #3631, #3664, #3700, #3436) — Thank you @sanil-23, @michaelk1957, and @mysma-9403!
Inference, embeddings, and observability hardening 🛡️
This range focuses heavily on making the app quieter, safer, and more resilient: OAuth requests now use a Codex-compatible client version; Responses API role/kind mismatches are fixed; extraction now caps max_tokens and correctly treats provider 402s as non-retryable to stop storms. Embeddings get multiple guardrails (refuse empty inputs, block chat-only custom endpoints with no embeddings API, and prevent LM Studio “no models loaded” floods). BYO provider 401/403 auth failures are demoted from Sentry, SQ

The Parallel Power Upgrade
This release brings a faster, more transparent desktop experience—more concurrency in chat, smoother reliability in memory flows, and easier access to diagnostics. 🚀
Highlights
Faster chat, more parallelism ⚡
Agent inference now runs concurrently instead of one-at-a-time—both across threads (no more single global active-thread lock) and within a thread via parallel “forked” turns. Cancellation is also hardened to be more cooperative and resilient under load. (#3633) — Thank you @senamakel!
Memory source reliability improvements 🧠
Memory sources now re-fetch when a session becomes authenticated, improving consistency and reducing flakiness in memory-source UI flows after reloads. This also adds test coverage to lock in the behavior. (#3621) — Thank you @sanil-23!
Smoother CI + test stability 🧪
CI and tests got a cleanup pass to eliminate multiple flaky/failing categories: removing stale UI assertions, fixing async race conditions in autosave/memory, and adjusting Playwright timeouts to reduce infrastructure flakes. Also includes a small UX regression fix where a join success toast could fail to fire due to an unmounting effect. (#3618, #3623) — Thank you @senamakel-droid and @sanil-23!
Always-on Developer & Diagnostics access 🛠️
Developer & Diagnostics settings are now always visible—no more “Developer Mode” gate. This surfaces the Settings section, related settings search entries, and the Intelligence “council” tab by default, with tests updated accordingly. (#3639) — Thank you @senamakel!
Contributor Credits
Thanks to everyone who contributed to this release: @github-actions[bot], @sanil-23, @senamakel, and @senamakel-droid.
Full Compare
https://github.com/tinyhumansai/openhuman/compare/v0.57.39...v0.57.40

The Intelligence Upgrade 🎉
v0.57.18 to v0.57.39 brings 125 PRs across 146 commits, with upgrades across memory, voice, agents, reliability, and developer foundations. Thank you to everyone who contributed to this release. ✨
Highlights 🚀
🎙️ Voice & hands-free control
Voice and hands-free control get more useful across the desktop, with always-on listening, global push-to-talk, faster command routing, and stronger automation paths for interacting with apps. (#3349, #3420, #3531, #3545, #3551, #3558, #3619) — Thank you @CodeGhost21, @sanil-23, @M3gA-Mind, and @oxoxDev!
🧠 Memory & intelligence
Memory and intelligence flows are faster, clearer, and more resilient, from source sync controls and richer ingest to batched embeddings and delegated memory retrieval. (#3413, #3417, #3418, #3421, #3422, #3424, #3428, #3438, #3439, #3441, #3444, #3446, #3447, #3454, #3459, #3479, #3480, #3499, #3521, #3578, #3580, #3583, #3586, #3587, #3590, #3598, #3611, #3613) — Thank you @sanil-23, @senamakel, @senamakel-droid, @oxoxDev, @graycyrus, and @michaelk1957!
✅ Tasks, chat & agent workflows
Task, chat, and agent workflows become easier to steer and inspect, with better task boards, persistent run state, safer delegation, and clearer model/thread controls. (#3388, #3399, #3411, #3412, #3419, #3426, #3443, #3456, #3457, #3458, #3477, #3481, #3483, #3497, #3500, #3519, #3528, #3530, #3532, #3533, #3544, #3546, #3553, #3555, #3556, #3562, #3563, #3564, #3581, #3584, #3591, #3594, #3596, #3597, #3600, #3601, #3607, #3610) — Thank you @senamakel, @graycyrus, @sanil-23, @senamakel-droid, @oxoxDev, @alexzhu0, and @YellowSnnowmann!
🔐 Reliability, security & platform polish
Reliability and platform behavior are tightened across security policy, credential handling, session health, CEF startup, Windows filesystem edge cases, and release-only build paths. (#3409, #3423, #3427, #3450, #3496, #3498, #3526, #3529, #3534, #3557, #3559, #3579, #3589) — Thank you @oxoxDev, @senamakel, @M3gA-Mind, and @sanil-23!
🧩 Integrations, UI & developer foundations
Integrations, UI polish, and developer foundations also move forward, including clearer connected-account surfaces, meeting-agent wiring, presentation/artifact improvements, and cleaner docs/code organization. (#3402, #3442, #3445, #3448, #3451, #3452, #3453, #3455, #3460, #3461, #3462, #3473, #3476, #3485, #3492, #3501, #3502, #3515, #3516, #3517, #3518, #3520, #3527, #3536, #3543, #3552, #3569, #3571, #3572, #3573, #3574, #3575, #3582, #3588, #3592, #3593, #3599, #3612, #3614) — Thank you @oxoxDev, @senamakel-droid, @senamakel, @YellowSnnowmann, @Sathvik-1007, @graycyrus, @sanil-23, and @alexzhu0!
New Contributors 🌟
- Welcome michaelk1957! Thank you for #3598 fix(memory): stop oversized/dense chunks from breaking bge-m3 embedding.
Hope you join the Discord for exclusive roles and contributor rewards!
Contributor Credits 🙌
- Alexzhu (#3536, #3543, #3544) — thank you!
- CodeGhost21 (#3349) — thank you!
- Cyrus Gray (#3399, #3518, #3533, #3569, #3573, #3574, #3575, #3578, #3580, #3581, #3582, #3586, #3592, #3593, #3594, #3599) — thank you!
- github-actions[bot] — thank you!
- Mega Mind (#3531, #3557, #3558, #3619) — thank you!
- michaelk1957 (#3598) — thank you!
- oxoxDev (#3402, #3409, #3496, #3497, #3498, #3499, #3500, #3501, #3527, #3546, #3551, #3552, #3553, #3556, #3583, #3596, #3600, #3601) — thank you!
- sanil-23 (#3411, #3412, #3413, #3417, #3420, #3477, #3519, #3520, #3521, #3545, #3562, #3563, #3579, #3587, #3588, #3591, #3607, #3610) — thank you!
- Sathvik Gilakamsetty (#3516) — thank you!
- Steven Enamakel (#3388, #3418, #3419, #3421, #3422, #3423, #3424, #3426, #3427, #3428, #3438, #3439, #3445, #3448, #3450, #3451, #3452, #3453, #3454, #3455, #3456, #3457, #3458, #3459, #3460, #3461, #3462, #3473, #3476, #3480, #3481, #3483, #3492, #3526, #3528, #3529, #3530, #3532, #3534, #3559, #3564, #3589, #3611, #3612, #3613, #3614) — thank you!
- Steven Enamakel's Droid (#3441, #3442, #3443, #3444, #3446

What's Changed
- refactor: improve matrix parsing validation and performance by @manucian-official in https://github.com/tinyhumansai/openhuman/pull/3129
- fix(inference/ollama): use prompt-guided tool calling so skills work on Ollama (#3098 sub-issue 3) by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3229
- feat(memory-tree): per-integration health strip (#2763) by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3230
- fix(channels/telegram): wire ApprovalGate end-to-end for Telegram turns (#3098 sub-issue 2) by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3232
- docs(claude.md): document action sandbox vs internal workspace split by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3241
- test(memory-sync): E2E + Vitest coverage for #3113 sync pipeline (#3116) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3194
- feat(voice): auto-send dictation transcript + allowlist app-launch commands (#3148 Phase 1) by @M3gA-Mind in https://github.com/tinyhumansai/openhuman/pull/3168
- fix(scripts): add short help to GitHub test map by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3223
- fix(scripts): add short help to stale CI cleanup by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3222
- docs: remove stale coverage matrix PR-local markers by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3220
- perf(learning): bounded-concurrency persist in transcript ingestion by @mysma-9403 in https://github.com/tinyhumansai/openhuman/pull/3234
- fix(orchestrator): force code-repo delegation when reading stalls (#3102) by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3214
- perf(memory_store): batch chunk embeddings in upsert_document by @mysma-9403 in https://github.com/tinyhumansai/openhuman/pull/3213
- fix(inference): actionable error for completion-only model 404 + unmistakable run_code failure (#3193) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3211
- feat(memory): pipeline hardening — typed failures, BYO embeddings, doctor, honest status by @zahica1234 in https://github.com/tinyhumansai/openhuman/pull/3076
- fix(agent_prompts): anchor coding-agent prompts in action_dir, not workspace_dir by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3242
- test(tools/system): lock in action_dir as the CWD for shell-family tools by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3243
- fix(shell): Windows pre-CEF cache-lock wait to stop relaunch panic (TAURI-RUST-F) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3210
- feat(mcp): sanitize remote tool descriptions + length caps by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3215
- feat(chat): Files in this chat — persistent per-chat artifact panel (#3024) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3026
- feat(backend_meet): integrate with backend gmeet bot via Socket.IO by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3182
- feat(settings): AgentAccessPanel reads live action_dir/workspace_dir via RPC by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3245
- feat(claude-code): Claude Code CLI provider — Phases 1–5 by @finedesignz in https://github.com/tinyhumansai/openhuman/pull/2472
- feat(security): explicit agent turn origin + fail-closed approval gate + memory provenance by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3227
- test(playwright): add functional UI flow coverage by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3257
- feat(sandbox): add real sandbox execution backends for agent tools by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3261
- fix(review): use exec and interactive mode for agent CLI invocations by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3262
- feat(inference): local provider profiles and MLX/generic-local support by @senamakel in https://github.com/tinyhumans

What's Changed
- Add vault file-system watcher implementation by @manucian-official in https://github.com/tinyhumansai/openhuman/pull/3183
- fix(subconscious): degrade WAL journal mode to fix Intelligence tab hang on shm-incompatible filesystems by @M3gA-Mind in https://github.com/tinyhumansai/openhuman/pull/3233
Full Changelog: https://github.com/tinyhumansai/openhuman/compare/v0.57.10...v0.57.11

What's Changed
- fix(agent): refresh orchestrator integration context on mid-session OAuth (#3044) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3153
- feat(memory): record real LLM cost in sync audit (#3110) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3150
- feat(agent/multimodal): support [FILE:…] markers with text extraction (#2777) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/2954
- feat(security): separate agent action sandbox from internal workspace state by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3074
- fix(inference): surface actionable error when Managed route fails with no credits by @senamakel-droid in https://github.com/tinyhumansai/openhuman/pull/3121
- fix(memory/safety): exclude bare-phone patterns from strict PII rejection (#2848) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/3028
- test: green Rust Core Coverage (stale assertions + env-race serialization) by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/3156
- fix(composio): complete connection-disconnect cleanup (config entry + memory tree) by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/3140
- feat(analytics): wire product event tracking by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3123
- refactor(agent): unwire eager 7-day memory-tree digest from turn loop (#3170) by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/3171
- docs: clarify script install verification status by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3066
- fix(scripts): make checklist help exit cleanly by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3067
- fix(scripts): normalize agent-batch help exits by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3068
- fix(scripts): add help to coverage gates by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3070
- fix(scripts): validate i18n bundle dist flag by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3071
- fix(scripts): reject invalid mock API ports by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3072
- test(scripts): run OpenClaw formatter tests without vitest by @alexzhu0 in https://github.com/tinyhumansai/openhuman/pull/3063
- fix(ai-settings): reset orphaned local-runtime routing when the runtime is disabled by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/3167
- revert: remove all Sentry error suppression (12 PRs) by @graycyrus in https://github.com/tinyhumansai/openhuman/pull/2959
- perf(memory_tree): batch drill_down BFS walker per depth by @mysma-9403 in https://github.com/tinyhumansai/openhuman/pull/3032
- fix(subagent): box-pin engine recursion to fix tokio worker stack overflow by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/3151
- refactor(composio): extract derive_toolkit_slug helper by @YOMXXX in https://github.com/tinyhumansai/openhuman/pull/3035
- fix(runtime): apply 16 MiB worker stack to desktop core + agent CLI runtimes (#3159) by @YOMXXX in https://github.com/tinyhumansai/openhuman/pull/3175
- fix(sentry): bind scope user at session boundaries + core boot (#3135) by @YOMXXX in https://github.com/tinyhumansai/openhuman/pull/3176
- fix(inference): normalize 0.0.0.0 to 127.0.0.1 in Ollama URL + add endpoint edit button by @senamakel-droid in https://github.com/tinyhumansai/openhuman/pull/3161
- feat: sync budget controls + agent activity level picker (#3117) by @senamakel-droid in https://github.com/tinyhumansai/openhuman/pull/3174
- feat(memory-sync): track Composio API action count + cost in sync audit (#3111) by @justinhsu1477 in https://github.com/tinyhumansai/openhuman/pull/3138
- fix(cron): make cron_run non-blocking, enqueue async execution (#3127) by @YellowSnnowmann in https://github.com/tinyhumansai/openhuman/pull/3142
- chore(ci): simplify release workflows — remove pretests, add commit picker and bump-only mode by @senamakel in https://github.com/tinyhuma

What's Changed
- fix(tools): additive-safe tool filter prevents stale snapshots from stripping cron tools by @senamakel-droid in https://github.com/tinyhumansai/openhuman/pull/3118
- fix(auth): resolve login redirect loop on first login by @senamakel-droid in https://github.com/tinyhumansai/openhuman/pull/3109
- feat(config): add UI control for agent action timeout (#3100) by @senamakel-droid in https://github.com/tinyhumansai/openhuman/pull/3112
- feat(memory): redesign sync flow with ingest_summary, graph improvements, audit log by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3113
- fix(auth): gracefully drop OAuth profiles with missing access_token by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3125
- test: fix flaky/stale tests blocking Rust E2E + coverage CI on main by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/3147
- fix(oauth): extend loopback listener lifetime 60s → 300s by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/3145
- feat(chat): auto-resize composer textarea to fit content by @graycyrus in https://github.com/tinyhumansai/openhuman/pull/3139
- fix(inference): accept reasoning field alias for thinking-mode providers by @senamakel-droid in https://github.com/tinyhumansai/openhuman/pull/3124
- feat(ui): hide dev-only features in production, clean up homepage by @senamakel in https://github.com/tinyhumansai/openhuman/pull/3157
Full Changelog: https://github.com/tinyhumansai/openhuman/compare/v0.57.4...v0.57.5