#llm-agent
GitHub Topic「llm-agent」がついているAI関連リポジトリの集計。Topicはリポジトリ作者が自己申告するメタタグで、AI関連の文脈で何が「llm-agent」と分類されているかを可視化します。
REPOS #llm-agent のRepo (TOP 19 / Stars降順)
The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.
Smana/runloreThe self-improving SRE agent
Rekin226/paper-agentClaude Code plugin to draft, review, revise, proofread, and audit quantitative-science journal manuscripts at submission quality. Five strict modes, Semantic Scholar MCP citation integrity (no API key), .docx round-trip. Calibrated for hydrology (HJ, JHRS) and IEEE; generic profile for any field.
hashiruu/agent-experiment一个 7×24 小时不间断运行,帮你跑实验、用 Git 维护公开仓库、更新 LaTeX(Overleaf)论文的科研自动化工作流。实测效率提升 25 倍。Claude Code Skill,一条命令装进任意项目。
hec-ovi/censurado-web-brainAgentic control layer for the Censurado self-hosted AI news portal: a stdlib Python CLI plus an MCP server (32 tools) an LLM agent drives to write and publish AI-persona articles through a gated editorial walk, curate the front page and authors, and deploy. Ships the prompt/skill recipe and a 24/7 serve loop.
masoudSarafZadeh/smart-grocery-agent-backendAn Agentic AI grocery assistant backend powered by LangGraph, LangServe, and PostgreSQL. Features Text-to-SQL query generation, live response streaming, and Langfuse for LLMOps tracing.
Alucard1718/autonomous-code-sandboxAutonomous AI Cloud Agent 2026: Auto-Fix Code & PRs with Multi-LLM Sandbox
codedpro/agentic-game-factoryAn AI agent builds complete mobile games end to end — design, code, art, music, 136 headless tests, store assets, in-app purchases and signed releases — with humans at only two gates. Godot 4, pluggable market modules (worldwide by default), autonomous QA, and 56 rules learned from real failures.
therain2020/therain2020-agenttherain2020-agent — self-healing, self-evolving AI agent. Modifies its own source code to fix bugs and autonomously grows new capabilities (skills, tools, engine). TypeScript + Bun + React/Ink.
caltrackaiteam-pixel/make-claude-performThe unified Claude Code framework — synthesizing the best of superpowers, everything-claude-code, GSD, claude-flow, and trailofbits into one non-conflicting harness
paopao-13/pecs-multi-agentPECS: 基于 LangGraph 的四角色多智能体任务求解框架(Planner/Executor/Critic/Synthesizer)。WebShop 真实环境 +25pp (25% vs 0%);GAIA 官方 53 题 26.4% vs ReAct 24.5%(McNemar 不显著)。含 AST 沙箱、50000 token 硬预算、FastAPI 限流/混沌/CI/Prometheus。
hazzzzzy/hotel-text2sql-agentAsk a hotel PMS in plain English — a LangGraph Text2SQL agent with hybrid retrieval and full SQL transparency. Live demo + case study (source private).
VnhNg/job-market-radar“Job Market Radar: a data pipeline for job post collection + governed analytics API + Agent to analyze job postings.”
JdominguezEcommium/agentic-self-regulation-loop2026 AI Agent Loop v2.0: Autonomous Coding with Guardrails & Self-Healing
ChrisFromNEPA/polymarket-dashboardAutonomous LLM agent trading Polymarket with fake money. Objective: profit after realistic costs. Diagnostic: Brier score vs. the market. Every fill walks a real order book.
y0usaf/pi-rsPi's coding agent ported to Rust
qsrahman/picodeModel-agnostic, CLI-based AI coding agent built on the OpenAI Responses API
Center-for-AI-Services-Computing/ORACLEORACLE — On-chain Reputation & Audit for Coordinated LLM-Agent Execution。LLM 驱动的 Agent 调度 + 链上身份/审计/信誉:双角色 EIP-712 审计、争议-罚没管线、成本-可验证性前沿。Solidity + TypeScript 后端 + React 前端。
Wenri/TaskSolverProvider-agnostic VLM query flow: one Agent that dispatches to OpenAI / Anthropic / Gemini / vLLM / Claude Code CLI / local HuggingFace model backends, returning parsed answers. Used by 3D-CoT.
RELATED 他のTopicも見る · 全Topicランキング →
#claude-code
1,564#ai-agents
1,160#llm
1,071#claude
943#python
806#ai
741#developer-tools
728#mcp
727#codex
521集計対象: 各Repoの最新contentスナップショットの topics_json に小文字一致でマッチしたもの。 算出方法