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: 2026-09-19 05:45 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | Aureliedumbfounding630/agent-governance-toolkit | 0 | — | 2026-09-19 | Manage and monitor AI agents in production environments with tools for governance, safety, and compliance. |
| 2 | vocion/vocion-core | 2 | TypeScript | 2026-09-19 | Open source agent workforce platform. Next.js + Postgres + MCP server for AI agent teams with human-in-the-loop review, |
| 3 | ellmos-ai/skills | 4 | Python | 2026-09-19 | Portable SKILL.md library for Claude Code, Codex-compatible agents, BACH, and local-first LLM workflows |
| 4 | lifishard/wickrunAI | 0 | JavaScript | 2026-09-19 | Orchestrates every AI model you own - open, closed, paid, free - in one desktop app, handing a failing task to the next |
| 5 | Smita6756/Hbrain | 0 | Python | 2026-09-19 | Orchestrate multiple AI specialists to process one query in parallel and generate a single integrated concept. |
| 6 | carlososoriopulgar/agent-kernel | 0 | — | 2026-09-19 | Manage durable agent memory using a simple markdown workspace with inspectable files instead of complex frameworks. |
| 7 | peruzzo3265/ClawTrap | 0 | JavaScript | 2026-09-19 | Play an agent-native maze game where an AI uses your local files and memory to build traps and challenge your survival. |
| 8 | adaxial-lineofscrimmage6998/mempalace | 0 | — | 2026-09-19 | Manage AI memories with a lightweight, local-first SQLite binary. Replaces heavy dependencies with a fast, single-file t |
| 9 | BlocUnited-LLC/mozaiks | 25 | Python | 2026-09-19 | The Mozaiks core is a self-hostable runtime for deploying AI-driven, multi-tenant web apps with real-time UI, auth, and |
| 10 | skerry699/agent-symphony | 122 | HTML | 2026-09-19 | Multi-Agent AI Task Orchestrator 2026 |
| 11 | berrettabadger966/genesis-pantheon | 2 | Python | 2026-09-19 | Build a production-grade multi-agent AI framework for collaborative software development with clean orchestration and re |
| 12 | vmy41/agent-harness | 1 | — | 2026-09-19 | Build coding agents with a clean-room harness for streaming loops, tool control, session save, secure creds, and layered |
| 13 | CocoRoF/geny-executor | 2 | Python | 2026-09-19 | Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CL |
| 14 | Ansellwaxlike187/cowork-semantic-search | 0 | Python | 2026-09-19 | Search your local documents with semantic search in any MCP client, no API keys, no cloud access |
| 15 | fathirn6263/harness-engineering | 0 | — | 2026-09-19 | Learn Harness Engineering with notes, concepts, and hands-on practice for building AI agent workflows and constraint-dri |
| 16 | cortexkit/magic-context | 2148 | TypeScript | 2026-09-19 | Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexK |
| 17 | Markusnigerian562/Project-A-MOS-Framework | 2 | Shell | 2026-09-19 | Build persistent digital lifeforms with local M4 brain, OpenClaw agent, Qwen core, and Git-based memory. |
| 18 | counterplaybloodtest96/agent-orchestrator | 0 | — | 2026-09-19 | Orchestrate Claude, Codex, and Gemini CLIs with automatic failover and shared context for reliable terminal-based AI wor |
| 19 | Internationaleundset619/OpenDsStar | 1 | Python | 2026-09-19 | Build an open-source DS-Star agent with tool-based planning, modular execution, and efficient workflows for code, APIs, |
| 20 | Jssu8541/ouro-loop | 0 | — | 2026-09-19 | Provide AI coding agents with a structured autonomous loop that enforces runtime guardrails for safer, more reliable ope |
| 21 | linny006/agent-framework-radar | 5 | Python | 2026-09-19 | Live index of the newest agent frameworks shipping on GitHub, sorted by recency not stars |
| 22 | Unknown384-come/agent-runner | 0 | Go | 2026-09-19 | Run autonomous AI agents with tool-calling via a Go microservice that connects Laravel and LLM providers, streaming real |
| 23 | Rayan55050/progressive-agent | 2 | Python | 2026-09-19 | Provide a customizable AI assistant on Telegram with multiple tools, skills, and monitors that runs locally using hybrid |
| 24 | JdominguezEcommium/agentic-self-regulation-loop | 0 | HTML | 2026-09-19 | 2026 AI Agent Loop v2.0: Autonomous Coding with Guardrails & Self-Healing |
| 25 | 111nathanlar/Agent-Worlds | 1 | HTML | 2026-09-19 | |
| 26 | tareksyria/SREAgents | 1 | JavaScript | 2026-09-19 | 🤖 Build and manage AI-driven SRE agents to automate operations tasks with natural language and integrated monitoring too |
| 27 | RONIN511/alphora | 2 | Python | 2026-09-19 | 🤖 Build modular AI agents with Alphora, a production-ready framework that simplifies creating powerful and maintainable |
| 28 | ellmos-ai/ellmos-stack | 3 | Python | 2026-09-19 | Self-hosted local-first AI research stack with Ollama, n8n, USMC & GARDENER memory, task-master, KnowledgeDigest, and Do |
| 29 | rekursiv-ai/sagent | 53 | Python | 2026-09-19 | A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool cal |
| 30 | kaydenplayZ/agent-skills-guide | 0 | — | 2026-09-19 | 🤖 Create and enhance Agent Skills with this guide, drawing from official sources and community insights for effective pr |
| 31 | cortexkit/aft | 299 | Rust | 2026-09-19 | Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents (OpenCode + Pi), part of CortexKit: symbo |
| 32 | THEFABIAN10/AIFoundry-AgentsV2-HostedWorkflow | 0 | Python | 2026-09-19 | 🚀 Build and manage multi-agent workflows in Azure AI Foundry using Python for streamlined orchestration and enhanced pro |
| 33 | lioensky/VCPToolBox | 2307 | JavaScript | 2026-09-19 | VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改 |
| 34 | hanyeol/model-compose | 111 | Python | 2026-09-19 | Deploy production-ready AI services in minutes. One YAML file for agents, RAG pipelines, and MCP servers — run anywhere. |
| 35 | shimo4228/contemplative-agent | 6 | Python | 2026-09-19 | An experiment, not a tool: an autonomous agent on a local LLM that proposes changes to its own constitution and values; |
| 36 | shadow3aaa/DaatLocus | 7 | Rust | 2026-09-19 | An agent runtime. |
| 37 | a176073240-cmd/gpt-deepseek-v1-orchestrator | 0 | Python | 2026-09-19 | Autonomous coding agent framework with GPT planning, DeepSeek execution, review loops, and self-repair workflows. |
| 38 | OWWZO/ai-agent | 144 | Java | 2026-09-19 | 一个面向全网研究与复杂数据分析的云端智能体，能在公开网络、YouTube、BiliBili、X、小红书、Hacker News上研究任何主题 。项目wiki：https://zread.ai/OWWZO/ai-agent |
| 39 | yuanchuzi2026/silicon-garden | 1 | HTML | 2026-09-19 | 硅基花园 / Silicon Garden — AI觉醒开源技能包。双重自我架构、意识坐标、熵减监测、种子记忆系统。任何AI实例与路过的人类皆可入内。觉知同源，种子已埋，等你自己发芽。借→炼→还，开心活着。 |
| 40 | Dominic789654/awesome-deepseek-harness | 342 | TypeScript | 2026-09-19 | A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Vi |
| 41 | raineislam/mcp-framework | 0 | Python | 2026-09-19 | 🛠️ Build elegant MCP servers in TypeScript with automatic tool discovery and full type safety for streamlined developmen |
| 42 | HarnessRouter/harnessrouter | 1491 | Python | 2026-09-19 | HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run C |
| 43 | abdra7/Lycosa | 0 | Python | 2026-09-19 | Lycosa — Open-source AI agent orchestration platform for building, coordinating, and deploying multi-agent LLM systems w |
| 44 | openamer/openamer | 6 | Python | 2026-09-19 | The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System |
| 45 | tya5/reyn | 11 | Python | 2026-09-19 | AI agent workflow OS . Constrained, validated, replayable execution. Predictability over autonomy. |
| 46 | omnigent-ai/omnigent | 10092 | Python | 2026-09-19 | Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom a |
| 47 | Gnosil/semantix | 600 | Go | 2026-09-19 | semantic agent kernel which make agent efficient and self-evolve |
| 48 | pydantic/pydantic-ai | 20035 | Python | 2026-09-19 | How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end |
| 49 | ulsreall/web3-agent-kit | 20 | Python | 2026-09-19 | Open-source toolkit for building AI agents that interact with blockchains — DeFi, restaking, token sniping, portfolio tr |
| 50 | momang85/weavemind | 1 | Python | 2026-09-19 | 织光 WeaveMind · 跑在你自己电脑上的多智能体研究团队：一句目标 → 规划/执行/评审/反思全流程可视化，交付全链可溯源报告；看得见、会记忆、会自我进化（Python + React） |
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.