Environnements d'exécution d'agents, frameworks d'orchestration et applications propulsées par des LLM. Nous recherchons des projets au modèle d'exécution clair, aux exécutions observables et qui documentent honnêtement ce que l'agent sait faire ou non.
497 dépôts dans cette catégorie
Recevez les meilleurs nouveaux dépôts de cette catégorie dans le panorama hebdomadaire.
Browserless Chrome uTLS + HTTP/2 OpenAI-compatible API daemon for Google Gemini Web (/v1/chat/completions & /v1/responses)
dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。
🐚 The AI assistant that just works. One self-hosted app for every model you already pay for: Claude Code, Codex, Copilot, Gemini, Ollama and more. Chat from your desktop, phone or Telegram.
The online judge for the LLM era. Every case is a real customer delivery: you work it with a coding agent, and your system is judged once it is live.
TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients.
Karpathy's understanding ladder as agent skills: auto-pick text, diagram, interactive HTML, or video storyboard for any explanation. Nothing cut. English + 中文.
Official Code for the paper "Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents "
PythonAucune licence détectéeCréé le Mis à jour la semaine dernière
Asamana is an AI-driven emergent narrative engine.
Local-first AI agent for Chrome: browser automation, web research, and data extraction with your own model.
A local-first multi-agent app development platform, built on PenguinHarness
AI Roadmap 2026: a beginner's path through Foundations, LLM Engineering, Agents, Evaluation, and Production, with verified free resources and a mini-project per layer
DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.
SpeakMore：口述成文，划词即译。开源、免费的语音输入与翻译工具，支持 Mac 与 Windows：语音输入、语音翻译、划词翻译。兼容 Gemini、OpenAI、通义千问、DeepSeek、Kimi、智谱 GLM、MiniMax 及任意 OpenAI 兼容服务，语音输入亦可完全在本机运行。附 Typeless 逆向分析。
Decides who gets your GPU. Chat, image and voice engines lease the card in turn instead of grabbing it, so two of them never load at once and crash each other. One Go binary, nothing else to install.
Research and writing can be automated. Authorship cannot. Evidence list + agent skills for spotting AI-produced papers no human stood behind.
39 MCP servers (488 tools) that give AI agents the Iranian web: Digikala, Torob, Divar, Snappfood, Jabama, MrBilit, Paziresh24, Taaghche, laws, tax, crypto, stocks, news and more. Prices in Toman.
⚡ The fastest open-source AI gateway — one Rust binary with a built-in console to route, secure, budget and observe every LLM call across OpenAI, Anthropic, Gemini, Bedrock and more.
First-class Linux packaging for DeepSeek Harness desktop — AppImage, .deb, .tar.gz for x64/arm64, built by native CI.
Strata minus the bullshit. clone, rsync to prod, compile and go
Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.
把微信接入你的 AI Agent（Grok / Muse / Claude 等）· Connect WeChat to your personal AI agent via official iLink
⚡ Autonomous reverse engineering engine & Model Context Protocol (MCP) server for binaries and applications in Systems Rust
Codex 风格的推理等级滑条（DeepSeek Harness 插件）：可拖动连续滑条 + 高档位渐变星尘特效
A Model Context Protocol (MCP) bridge enabling Claude Desktop to execute tasks via the Google Antigravity CLI (agy).