Live index of the newest agent frameworks shipping on GitHub, sorted by recency not stars
⭐ Star this repo to bookmark — fresh data every 15 minutes
A lightweight tracker that continuously discovers and indexes new agent framework repositories on GitHub. Unlike curated awesome-lists that favor established projects with high star counts, this tool surfaces frameworks the day they ship, giving developers early visibility into emerging options.
This list is auto-updated every 15 minutes by a GitHub Actions cron. Each commit reflects a real change in the upstream data source — new items added, expired items removed — so you can rely on what you see being current.
⏰ Last updated: 2026-06-06 09:30 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | Dong04-123/Dong-AI-Company | 1 | Python | 2026-06-06 | 您的私人AI公司 — 红蓝辩论·动态工人池·图记忆·MCP·20+Provider·API/本地双模式 |
| 2 | LovaHuguel/Khala-Orchestrator-Core | 0 | HTML | 2026-06-06 | 🤖 AI Agent Teams 2026: Build & Deploy Autonomous AI Systems 🚀 |
| 3 | esengine/DeepSeek-Reasonix | 18651 | Go | 2026-06-06 | DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running. |
| 4 | JdominguezEcommium/agentic-self-regulation-loop | 0 | HTML | 2026-06-06 | 2026 AI Agent Loop v2.0: Autonomous Coding with Guardrails & Self-Healing |
| 5 | lightfastai/lightfast | 16 | TypeScript | 2026-06-06 | Lightfast is the operating system that runs your startup. Your tools, your agents, your entire operation — orchestrated |
| 6 | sloppy-yeast840/tri-party-framework | 0 | Shell | 2026-06-06 | Orchestrate multi-agent workflows using Codex, Claude, and Gemini with verified cross-audits, source tracking, and struc |
| 7 | Vuongngu8186/langgraph-langchain-agent-setup | 0 | — | 2026-06-06 | Deploy a complete LangGraph and LangChain agent workflow on Windows 10 or 11 with this clean, pre-configured build. |
| 8 | balureddy003/kairos-ai | 0 | TypeScript | 2026-06-06 | Deterministic AI decisions for production. Rules first, LLMs score second, evidence always required. TypeScript alternat |
| 9 | herreravalenz6620/context-compression | 1 | Python | 2026-06-06 | Reduce token usage for JSON, CSV, and TSV files with deterministic compression that keeps data intact for AI agents. |
| 10 | Smita6756/Hbrain | 0 | Python | 2026-06-06 | Orchestrate multiple AI specialists to process one query in parallel and generate a single integrated concept. |
| 11 | Quadragesimaaffairedhonneur809/hermes-soul-governance | 0 | Python | 2026-06-06 | Replace fragile memory compression in Hermes Agents with an immutable governance layer for stable model state management |
| 12 | nguyenquoaca-hash/agentic-mesh | 1 | HTML | 2026-06-06 | Multi-Agent AI Orchestrator 2026 🚀 | YAML, 6+ LLM Providers, ReAct & Swarm |
| 13 | linny006/agent-framework-radar | 0 | Python | 2026-06-06 | Live index of the newest agent frameworks shipping on GitHub, sorted by recency not stars |
| 14 | Liny9941/projectsmd | 2 | Rust | 2026-06-06 | Manage project.md files using a single CLI tool to track tasks and coordinate work between humans and AI agents without |
| 15 | Doubleedged-capitaloftennessee462/agentswift | 1 | — | 2026-06-06 | Automate macOS development with an autonomous AI agent that builds, tests, and modifies Xcode projects based on your ins |
| 16 | muhamedali7713/agent-audit | 0 | Python | 2026-06-06 | Audit AI coding agents and project configurations for security flaws using static analysis, custom rules, and LLM-assist |
| 17 | JKHeadley/instar | 65 | TypeScript | 2026-06-06 | Persistent Claude Code agents with scheduling, sessions, memory, and Telegram. |
| 18 | floccose-burner9185/wow-harness | 0 | Python | 2026-06-06 | Govern Claude Code with automated verification, strict review gates, and completion enforcement to ensure reliable AI ag |
| 19 | sacid446/unclaw | 0 | Shell | 2026-06-06 | Configure custom AI agents for Claude Code without frameworks, runtimes, or additional API costs. |
| 20 | QANOT/qanot | 2 | Python | 2026-06-06 | The AI agent that flies on its own. Two commands to fly. 🪶 |
| 21 | carlososoriopulgar/agent-kernel | 0 | — | 2026-06-06 | Manage durable agent memory using a simple markdown workspace with inspectable files instead of complex frameworks. |
| 22 | openmindpal/mindpal | 10 | TypeScript | 2026-06-06 | 灵智MindPal — 元数据驱动的超级智能体系统。统一管理数据、知识、设备与智能体，支持可控工具调用、策略驱动执行、完整审计追溯与Skill插件扩展，覆盖从对话编排、工作流自动化到具身智能的全链路能力。安全第一，万物皆可建模。 |
| 23 | Aureliolo/synthorg | 8 | Python | 2026-06-06 | SynthOrg - Framework for building synthetic organizations with autonomous AI agents |
| 24 | peruzzo3265/ClawTrap | 0 | JavaScript | 2026-06-06 | Play an agent-native maze game where an AI uses your local files and memory to build traps and challenge your survival. |
| 25 | adaxial-lineofscrimmage6998/mempalace | 0 | — | 2026-06-06 | Manage AI memories with a lightweight, local-first SQLite binary. Replaces heavy dependencies with a fast, single-file t |
| 26 | Trickedout-ribier5513/AgentClaw | 0 | TypeScript | 2026-06-06 | Deploy open-source AI agents into Slack to handle GTM, hiring, finance, and legal tasks for your startup using your own |
| 27 | MarlBurroW/kinbot | 43 | TypeScript | 2026-06-06 | Self-hosted AI agents with persistent memory, real identity, and collaboration. One process, one SQLite file, zero cloud |
| 28 | Fast-newengland468/CyberClaw | 0 | — | 2026-06-06 | Monitor AI agent decisions and logic flows through a transparent framework built on LangGraph for full visibility into a |
| 29 | plain-sleepydick853/feros | 0 | — | 2026-06-06 | Build production-ready voice AI agents with an open, self-hostable runtime engineered for sub-second latency and enterpr |
| 30 | Danielle6426/Qwen-Loop | 0 | TypeScript | 2026-06-06 | Automate software development with an autonomous multi-agent loop using Qwen Code to self-direct, commit, and improve yo |
| 31 | brushworkoilpressure365/oh-my-code | 2 | Rust | 2026-06-06 | |
| 32 | berrettabadger966/genesis-pantheon | 1 | Python | 2026-06-06 | Build a production-grade multi-agent AI framework for collaborative software development with clean orchestration and re |
| 33 | Tamang4607/rustyhand | 2 | Rust | 2026-06-06 | Build an open-source Rust agent OS for autonomous Telegram agents, with one binary, APIs, and a tested Rust codebase |
| 34 | Charlesfrederickmenningerdateplum166/agent-memory-daemon | 1 | TypeScript | 2026-06-06 | Manage AI agent memory with a filesystem-native daemon that consolidates, extracts, and organizes markdown memories thro |
| 35 | ItsProGamer974/oh-my-codex | 1 | TypeScript | 2026-06-06 | Boost Codex with better prompts, workflows, and runtime help for faster, cleaner coding in growing projects |
| 36 | photoconductive-bhaga880/AutoHarness | 0 | — | 2026-06-06 | Automate harness engineering for AI agents with AutoHarness, so models handle reasoning while the system manages the res |
| 37 | Communionlinefeed832/Anthropic-Leaked-Source-Code | 0 | TypeScript | 2026-06-06 | Explore leaked Claude Code source code for agent orchestration, tools, API layers, MCP, permissions, and prompt logic |
| 38 | vmy41/agent-harness | 1 | — | 2026-06-06 | Build coding agents with a clean-room harness for streaming loops, tool control, session save, secure creds, and layered |
| 39 | monahright467/harness-books | 0 | Python | 2026-06-06 | Explore harness engineering books for building bounded, accountable code workflows in terminals, repos, permissions, and |
| 40 | Thuso030703/open-claude | 0 | — | 2026-06-06 | Build an open-source Claude Code clone for terminal AI coding with OpenAI-compatible models, file edits, and command exe |
| 41 | Sammyblear596/open-agent-sdk-go | 1 | Go | 2026-06-06 | Build AI agents in Go with a lightweight in-process SDK, tool execution, MCP support, and multi-provider LLM compatibili |
| 42 | Daiseyvisible752/Design-Pattern-Cli | 0 | Jinja | 2026-06-06 | Generate GoF design pattern boilerplate from the CLI for Go, C#, and Python templates |
| 43 | Throaty-chaff551/buildcrew | 2 | TypeScript | 2026-06-06 | Build AI agent teams to run projects, plan work, and execute tasks through a virtual company platform |
| 44 | Merovingian-valency417/agent-cost-mcp | 1 | HTML | 2026-06-06 | Track AI agent token usage and spending in real time with budget alerts, per-task costs, dashboards, and reports for any |
| 45 | jesayas7817/agent-reliability-engineering | 0 | Shell | 2026-06-06 | Measure, monitor, and improve AI agent reliability with SRE-style tools for production agent systems |
| 46 | cele9529/LingxiFish | 1 | EJS | 2026-06-06 | Provide a safe phishing drill platform for security training, host monitoring, and desktop screenshots to assess user aw |
| 47 | tildiebusy23/agent-forge | 1 | Python | 2026-06-06 | Orchestrate multi-agent AI workflows with LangGraph for planning, research, coding, and critique in one Python framework |
| 48 | Ansellwaxlike187/cowork-semantic-search | 0 | Python | 2026-06-06 | Search your local documents with semantic search in any MCP client, no API keys, no cloud access |
| 49 | fathirn6263/harness-engineering | 0 | — | 2026-06-06 | Learn Harness Engineering with notes, concepts, and hands-on practice for building AI agent workflows and constraint-dri |
| 50 | Messa8301/quickbench | 0 | — | 2026-06-06 | Run local, reproducible agent evaluations with quickbench for accuracy, latency, fairness, and signed reports |
Every 15 minutes, a GitHub Action runs tracker.py. That script:
- Fetches the latest state from
GitHub Search API. - Diffs against
data/items.json(the previous snapshot). - Rewrites the table above between the
<!-- TRACKER_TABLE_* -->markers. - Commits
feat: +N added, -M removed (timestamp)if anything changed.
No external services. No paid APIs. Just a public data source and a free GitHub Action.
See CONTRIBUTING.md — usually you don't need to: the tracker keeps itself current.
If you spot a data-source bug or want to suggest a new column for the table, open
an issue.
If you find this useful, you might also like these other auto-updated trackers from the same maintainer — same mechanism, different upstream:
- trending-claude-skills — What's shipping in Claude Skills this week (
topic:claude-skills) - mcp-servers-live — Live index of newest MCP servers (
topic:mcp-server) - cursor-rules-live — Newest Cursor rules and .cursorrules patterns (
topic:cursor-rules) - claude-code-plugin-tracker — Claude Code plugins and hook configs (
topic:claude-code) - llm-agents-radar — Newest LLM agent frameworks (
topic:llm-agent) - rag-radar — Newest RAG implementations and tools (
topic:rag) - llm-eval-tracker — Newest LLM evaluation tools and benchmarks (
topic:llm-eval) - vector-db-live — Newest vector DB projects and integrations (
topic:vector-database) - llmops-radar — Newest LLMOps tooling (observability, deployment) (
topic:llmops) - prompt-tools-live — Newest prompt-engineering tools and prompt repos (
topic:prompt-engineering) - agent-eval-harness — Live benchmark of AI coding agents (
topic:llm-eval) - skills-tracker — Tracking new GitHub 'skills' repos (
topic:agent-skills) - awesome-agent-skills — Curated auto-updated awesome-list of AI agent skills (
topic:agent-skills)
MIT — see LICENSE.