Suositut: Tiedot päivitetty 16. marraskuuta 2026

Kategoriat

Internet1 415
Viestintä328
Ääni ja video937
Grafiikka ja suunnittelu561
Toimisto ja tuottavuus1 177
Kehitystyökalut3 280
Tekoälytyökalut605
Tietoturva ja yksityisyys407
Järjestelmätyökalut3 183
Pelit544
Opiskelu ja tiede241
Verkko ja IT292

Lataa LobeHub 2.2.9

An open-source, modern-design AI chat framework. Supports Multi AI Providers (OpenAI / Claude 4 / Gemini / Ollama / DeepSeek / Qwen), Knowledge Base (file upload / knowledge management / RAG), Multi-Modals (Plugins/Artifacts) and Thinking.

LobeHub Tekoälyavustajat ja kielimallit #15 Tekoälyavustajat ja kielimallit
Tämä on vanhempi versio. Uusin versio on 2.3.3. LobeHub 2.3.3 · Julkaistu:

Asennustiedostot 2.2.9

ArkkitehtuuriTyyppiLaajuusTiedostokokoLatausSHA256
64-bittinen EXE (NSIS) Nykyinen käyttäjä — github.com VirusTotal
64-bittinen EXE (NSIS) Kaikki käyttäjät — github.com VirusTotal

Linkki ja SHA256-tiiviste ovat peräisin Windows Package Managerin yhteisön manifestista. Vertaa ladatun tiedoston tiivistettä ennen kuin suoritat sen.

Muutosloki

This release was automatically published from PR #16406.
Changes
See PR description: https://github.com/lobehub/lobehub/pull/16406
Commit Message
🚀 LobeHub Release (20260629)
Release Date: June 29, 2026
Since v2.2.8: 199 merged PRs · 199 commits · 14 contributors
This weekly patch strengthens the agent execution loop: tasks can be verified with evidence, heterogeneous runs recover more reliably, and desktop, CLI, workspace, and provider workflows get clearer control surfaces.

✨ Highlights
- Heterogeneous agent reliability — Routes gateway and external-agent runs through shared lifecycle hooks, persists operation traces, records provider/model details, and keeps bounded verification armed. (#16102, #16193, #16237, #16302, #16386, #16393)
- Task and group continuity — Keeps creator context, assignee activity, group identity, real member rosters, and final answers stable across task handoffs and multi-agent conversations. (#16162, #16188, #16213, #16228, #16303, #16315, #16352, #16363, #16385, #16399)
- Desktop and CLI control — Adds CLI self-update and verify commands, desktop completion notifications, overloaded Claude Code auto-retry, tab/window fixes, hotkeys, and safer local search limits. (#16052, #16147, #16164, #16190, #16277, #16281, #16309, #16384, #16396)
- Provider and model compatibility — Updates OpenAI SDK/runtime mapping, Bedrock key auth, contextual pricing, GLM-5.2 handling, Zhipu stream controls, Copilot parameter filtering, Kimi thinking preservation, and Doubao Seed models. (#16090, #16128, #16135, #15722, #16204, #16240, #16284, #16331, #16401)
- Connectors and integrations — Improves custom connectors, legacy MCP migration, context-aware tool manifests, Aihubmix base URLs, Search1API auto engine selection, PostHog skill integration, and MCP marketplace handling. (#15912, #16172, #16180, #16210, #16233, #16311, #16328, #16282)

🏗️ Core Agent & Architecture
Task and Verify
- Task lifecycle — Task creation now records creator conversation origin, supports task-level verify storage, links created task IDs to detail pages, includes subtask activity, and bridges finished task handoff back to the creator conversation. (#16111, #16113, #16213, #16238, #16296, #16303, #16399)
- Verification reports — Verify runs gain standalone ingestion/init/delete, evidence submission, acceptance injection, final report pages, table/mobile report layouts, and builder-captured evidence. (#16132, #16140, #16163, #16164, #16187, #16214, #16260, #16391)
- Agent Builder context — Builder suggestions, feedback loops, document-to-skill conversion, editing-agent context, and heterogeneous-agent discovery make agent setup and repair more direct. (#15939, #16225, #16292, #16326)
Conversations, Groups, and Runtime
- Shared run lifecycle — Chat, gateway, and heterogeneous execution continue converging on the shared lifecycle with transport-driven completion, unified run modules, auto-title generation, and terminal error surfacing. (#16083, #16086, #16102, #16119, #16151, #16155)
- Group identity stability — Group reads, persisted messages, supervisor replies, council rendering, member roster injection, and topic routing now preserve group identity across nested and server-runtime flows. (#16149, #16152, #16154, #16188, #16228, #16259, #16271, #16313, #16352, #16363)
- Tool-heavy turn handling — Conversation grouping keeps toolless prose, terminal errors, trailing bookkeeping tools, and post-tool answers readable without hiding the final answer. (#16084, #16127, #16278, #16377, #16385)

📱 Platforms & Integrations
Desktop, CLI, and Devices
- Desktop UX — Desktop tabs, dynamic route meta, workspace-scoped navigation, completion notifications, update prompts, working directory actions, and transient network handling are more predictable. (#16089, #16184, #16190, #16206, #16224, #16252, #16273, #16276, #16309, #16355, #16384, #16396)
- CLI workflows — lh update, verify skill initialization, verify run deletion, file-search result caps, worker isolation, and CLI version bumps tighten local operation loops. (#16052, #16139, #16143, #16164, #16200, #16281, #16391)
- Devices and mobile routes — Workspace device support, scoped device lists, device deletion controls, remote-device tracing, and mobile router exposure for plugins and agent skills improve cross-device workflows. (#16134, #16191, #16280, #16295, #16299, #16333, #16360, #16371)
Providers, Models, and Tools
- Provider compatibility — OpenAI SDK v6, runtime model ID mapping, Bedrock API key auth, DeepSeek reasoning handling, GLM-5.2 metadata, Zhipu stream toggles, and Copilot payload filtering reduce provider-specific failures. (#16090, #16128, #16240, #16284, #16294, #16331, #16401)
- Model and pricing updates — Contextual model pricing, Aihubmix backup URLs, Kimi preserveThinking, Doubao Seed 2.1 models, NewAPI pricing optimization, and model-list search polish keep provider configuration fresher. (#15656, #15722, #16135, #16204, #16279, #16328)
- Connectors and tool rendering — Custom connector edit/delete, legacy MCP migration guards, context-aware manifests, real task/agent tool-card data, compact Linear cards, and local device scope tracing improve tool usage in agent flows. (#15912, #16172, #16180, #16272, #16311, #16359, #16280)

🖥️ Product Experience
- Agent-facing UI — Inbox interaction tools, memory editing persistence, image reference upload, human-approval notification island, "don't ask again" approval options, and sidebar/home labels refine daily agent work. (#15682, #16195, #16207, #16357, #16389, #16390)
- UI platform migration — Modal, Tabs, Switch, SplitButton, model-list search, route meta, devtools rows, and settings skill copy continue moving toward the base-ui and static-style conventions. (#16212, #16229, #16227, #16253, #16335, #16336, #16348)

🔧 Reliability, Tooling & Documentation
- Runtime reliability — Message-list SWR write-through, revalidation dedupe, IndexedDB cache retention, topic metadata serialization, task deadlock fixes, and unavailable-model notices reduce stale or stranded UI states. (#15927, #16131, #16211, #16285, #16301, #16383)
- Developer and deployment tooling — Local dev proxy matching, dev auth proxy NO_PROXY handling, automated testing port allocation, Docker ParadeDB pg_search, and MCP marketplace issue handling improve maintenance paths. (#16096, #16247, #16248, #16282, #16287, #16353)
- Documentation — UX surface interaction principles, DB enum guidance, and the June 22 weekly changelog are included for contributors and operators. (#16168, #16203, #16234)

👥 Contributors
Thanks to @sxjeru, @YOYO-do, @ZhuYuxuan9302, @Duo-Huang, @arvinxx, @Innei, @tjx666, @AmAzing129, @rdmclin2, @ONLY-yours, @sudongyuer, @cy948, @nekomeowww, and @rivertwilight.
Full Changelog: https://github.com/lobehub/lobehub/compare/v2.2.8...v2.2.9

https://github.com/lobehub/lobehub/releases/tag/v2.2.9

Suosituin kategoriassa Tekoälyavustajat ja kielimallit

Näytä kaikki
  1. Claude CodeTekoälyavustajat ja kielimallit · Anthropic PBC
  2. Codex CLITekoälyavustajat ja kielimallit · OpenAI, Inc.
  3. ChatGPT by lencxTekoälyavustajat ja kielimallit · lencx
  4. GPT4AllTekoälyavustajat ja kielimallit · Nomic
  5. JanTekoälyavustajat ja kielimallit · Jan
  6. oh-my-piTekoälyavustajat ja kielimallit · Can Bölük
  7. T3 CodeTekoälyavustajat ja kielimallit · T3 Tools
  8. CC SwitchTekoälyavustajat ja kielimallit · farion1231
  9. WSL ManagerTekoälyavustajat ja kielimallit · Bostrot
  10. LobeHubTekoälyavustajat ja kielimallit · LobeHub

Tunnisteet

Jaa