Gewild: Data bygewerk 27 Oktober 2026

Kategorieë

Internet1 356
Kommunikasie321
Klank en video898
Grafika en ontwerp539
Kantoor en produktiwiteit1 124
Ontwikkelaarsgereedskap3 134
KI-gereedskap529
Sekuriteit en privaatheid385
Stelselgereedskap3 114
Speletjies523
Onderwys en wetenskap239
Netwerk en IT284

codeg 0.20.0 aflaai

Aggregate and browse AI coding agent sessions (Claude Code, Codex, Gemini CLI, etc.) in one place. Desktop app, self-hosted server, or Docker.

Dit is ’n ouer weergawe. Die nuutste weergawe is 0.40.0. codeg 0.40.0 · Vrygestel:

Installeerlêers 0.20.0

ArgitektuurTipeBestekLêergrootteAflaaiSHA256
64-bis EXE (NSIS) Huidige gebruiker — github.com VirusTotal
ARM64 EXE (NSIS) Huidige gebruiker — github.com VirusTotal

Die skakel en SHA256 kom uit die gemeenskapsmanifes van die Windows-pakketbestuurder. Vergelyk die hashwaarde van die afgelaaide lêer voordat u dit laat loop.

Vrystellingsnotas

- feat(acp): Meet Grok Build — the 11th built-in agent. xAI's Grok Build joins codeg as a first-class coding agent: sign in with your xAI API key, choose its model and reasoning effort, delegate sub-agents, and manage its MCP servers — with live and replayed sessions rendered exactly like every other agent.
- feat(science): A new Scientific Research skills mode. Thirteen curated, open-source research skills (from K-Dense-AI's scientific-agent-skills) now ship alongside the bundled expert and office skills. Install them to the shared library, enable them per agent in Settings, and start from the new "Scientific Research" tab on the new-conversation screen — localized in all 10 languages.
- feat(chat): The composer and your sent messages are now plain text. What you type, and the messages you've already sent, display as clean plain text with file and session references shown as compact badges — so your input reads exactly as written instead of being reflowed as Markdown. (Assistant replies are unchanged and still render Markdown.)
- fix(chat): Background tasks now settle correctly. A background task that's been collected or stopped is now marked as finished, so its indicator no longer lingers as if it were still running.
- fix(chat): The model picker stays open while you use its scrollbar. Dragging the scrollbar inside the model list no longer dismisses the picker.

https://github.com/xintaofei/codeg/releases/tag/v0.20.0

Gewildste in KI-assistente en LLM’s

Sien alles
  1. Claude CodeKI-assistente en LLM’s · Anthropic PBC
  2. Codex CLIKI-assistente en LLM’s · OpenAI, Inc.
  3. ChatGPTKI-assistente en LLM’s · lencx
  4. GPT4AllKI-assistente en LLM’s · Nomic
  5. JanKI-assistente en LLM’s · Jan
  6. WSL ManagerKI-assistente en LLM’s · Bostrot
  7. oh-my-piKI-assistente en LLM’s · Can Bölük
  8. T3 CodeKI-assistente en LLM’s · T3 Tools
  9. CC SwitchKI-assistente en LLM’s · farion1231
  10. LobeHubKI-assistente en LLM’s · LobeHub

Etikette

Deel