ai-agents
Tracked open-source repos tagged ai-agents, sorted by stars.
- #541
Agent工程师最全学习路径 · 从零精通 AI 工程 · 20 阶段 503 课 · 中文全量翻译 + 配套站点 + 动画讲解视频 · 如何成为 AI Agent 工程师的修成指南
★ 1,047+21Star change over the last 7 days - #542
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.
★ 1,044+78Star change over the last 7 days - #543
DeepSeek Harness (DSH) ecosystem: curated plugins, tools, and infrastructure from dsh-external/hub and the public dsh-plugin topic.
★ 1,039+55Star change over the last 7 days - #544★ 1,037+8Star change over the last 7 days
- #545
Agentlens is a trusted agent trading platform. Here, you can quickly find the Agent that meets your needs, and you can also publish your own Agent to turn it into your digital asset. We encourage everyone to transform their areas of expertise into Agents and turn them into digital assets, allowing others to see your unique strengths.
★ 1,034-1Star change over the last 7 days - #546
Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes.
★ 1,030+2Star change over the last 7 days - #547
Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.
★ 1,027+45Star change over the last 7 days - #548
Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.
★ 1,025+13Star change over the last 7 days - #549
复刻网站的 Agent Skill:抓只读镜像、从压缩代码逐行还原、自动比对验收。An agent skill that mirrors a website, rebuilds it from the minified code, and verifies the result with automated diffs.
★ 1,024+248Star change over the last 7 days - #550★ 1,017+23Star change over the last 7 days
- #551
An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.
★ 1,016+50Star change over the last 7 days - #552★ 1,010+19Star change over the last 7 days
- #553★ 1,009+6Star change over the last 7 days
- #554
A curated list of plugins for DeepSeek Harness (dsh) - DeepSeek Harness plugin ecosystem
★ 1,005+13Star change over the last 7 days - #555
Web UI for AutoGen (A Framework Multi-Agent LLM Applications)
★ 1,004-1Star change over the last 7 days - #556
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree
★ 1,003+4Star change over the last 7 days - #557
Free, open-source anti-detect browser launcher for web scraping and multi-accounting. By the ProxyShard team. Engine-level fingerprint spoofing in Chromium 148 (WebGL / WebGPU / Client Hints / fonts / TLS), 170+ device profiles bundled, stable QUIC + WebRTC over SOCKS5.
★ 1,002+184Star change over the last 7 days - #558
Open-source platform that unifies AI agent orchestration and workflow automation — autonomy and precision in one platform.
★ 1,000+2Star change over the last 7 days - #559
📚 Real-world OpenClaw automation examples from Moltbook
★ 999-1Star change over the last 7 days - #560
Delegate tasks to Codex and Gemini directly from within Claude Code.
★ 996+0Star change over the last 7 days - #561
Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications
★ 996-1Star change over the last 7 days - #562
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.
★ 993+4Star change over the last 7 days - #563
🚀 The definitive roadmap to becoming a Forward Deployment Engineer (FDE). Master AI Agents, Enterprise Data Architecture, and Strategic Consulting. Bridging the gap between HQ and the field. Inspired by the "Delta" role at Palantir, OpenAI, and Scale AI.
★ 993+20Star change over the last 7 days - #564
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
★ 990+13Star change over the last 7 days - #565
AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual TUI. It is designed to automate security assessments, penetration testing, and bug bounty reconnaissance — without any API keys or cloud dependency.
★ 986+6Star change over the last 7 days - #566
from vibe coding to agentic engineering - practice makes codex perfect
★ 985+6Star change over the last 7 days - #567
🚀 A real-time monitoring dashboard for Claude Code & Codex, built with SQLite3, Node.js, Express, React, Vite, TailwindCSS, & WebSockets. It tracks sessions, agent activity, tool usage, and subagent orchestration, providing live analytics, a Kanban status board, status notifications, a cute buddy, & an interactive web UI/MacOS/Windows native app.
★ 984+21Star change over the last 7 days - #568★ 973+3Star change over the last 7 days
- #569
The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers.
★ 973+0Star change over the last 7 days - #570
Free AI Agents Resources – Your All-in-One 2026 Learning Hub
★ 967+9Star change over the last 7 days