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: 2026-10-25 16:45 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | human-plus-machine/monkeybot | 3 | Python | 2026-10-25 | Universal Agent Harness |
| 2 | yurika0211/lucky-agent | 15 | Go | 2026-10-25 | LuckyAgent — 注重长任务规划和系统记忆性的Agent框架 |
| 3 | Opita-Code/opita-code | 0 | TypeScript | 2026-10-25 | Opita Code — vibe-studio runtime, arquitectura y cumplimiento |
| 4 | orhun/voff | 10 | Rust | 2026-10-25 | Workflow builder for coding agents 🐶 |
| 5 | miuuyy/Octopus-SI-OS | 309 | Rust | 2026-10-25 | A self-evolving agentic OS. A new architecture for agent execution, built on operating-system principles, with the harne |
| 6 | futuregene/future-os | 110 | Rust | 2026-10-25 | One AI agent, everywhere you work — terminal, desktop, mobile, and your chat apps. Rust core. |
| 7 | vicfei/growbuddy | 0 | Python | 2026-10-25 | Self-evolving AI agent runtime — RSI under tiered authority, reversible hash-chained ledger, capability security, and cr |
| 8 | swombat/souls-house | 45 | Ruby | 2026-10-25 | A platform for hosting persistent AI agents that live, rather than stateless assistants that wake, perform, and vanish. |
| 9 | Ash20pk/BerthOS | 1 | TypeScript | 2026-10-25 | A persistent, kernel-permissioned sandbox for AI agents — real filesystem, browser, and shell, not a bag of stateless AP |
| 10 | cmm00100/DreamRole | 1 | Python | 2026-10-25 | 一个自己用的 agent。双击就能用，不需要装 Python、不需要开浏览器。 |
| 11 | vocion/vocion-core | 2 | TypeScript | 2026-10-25 | Open source agent workforce platform. Next.js + Postgres + MCP server for AI agent teams with human-in-the-loop review, |
| 12 | matheusbuniotto/pydantic-ai-durable | 0 | Python | 2026-10-25 | Crash-resilient, durable agent harness for PydanticAI: resumable runs, SQLite storage, approvals, sagas |
| 13 | bigduu/Bamboo-agent | 21 | Rust | 2026-10-25 | Bamboo — a local-first Rust agent harness and runtime with sessions, tools, skills, MCP, sub-agents, workflows, schedule |
| 14 | yangheng95/opencorvus | 308 | TypeScript | 2026-10-25 | DIY your own agent team harness for long-horizon agent work |
| 15 | xanstomper/mochi | 2 | TypeScript | 2026-10-25 | Mochi — a minimal, fast, autonomous coding agent for the terminal. Goals, task DAGs, multi-agent teams, persistent HTTP |
| 16 | dshakes/lantern | 1 | TypeScript | 2026-10-25 | Production runtime for AI agents — run the whole stack locally with one command, ship to your own cloud. Real WhatsApp/S |
| 17 | cortexkit/aft | 332 | Rust | 2026-10-25 | Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents (OpenCode + Pi), part of CortexKit: symbo |
| 18 | SourceShift/mini-ork | 32 | Python | 2026-10-25 | Prove an AI-written fix actually fixes the bug. mini-ork certify reproduces the bug against your repo's own code, attack |
| 19 | kindgi/kindgi-sdk | 3 | TypeScript | 2026-10-25 | Kindgi SDK — public Apache-2.0 packages for building on Kindgi (preview) |
| 20 | esengine/DeepSeek-Reasonix | 35959 | Go | 2026-10-25 | A reliable coding agent for complex software engineering tasks. |
| 21 | shibing624/agentica | 357 | Python | 2026-10-25 | One person, a team of agents: CLI, Web, Desktop & Python SDK with multi-session collaboration, persistent memory, and se |
| 22 | linny006/agent-framework-radar | 8 | Python | 2026-10-25 | Live index of the newest agent frameworks shipping on GitHub, sorted by recency not stars |
| 23 | Soodok/Deepseek-Harness-Local-Android | 343 | Kotlin | 2026-10-25 | Run the DeepSeek Harness AI agent natively on Android — no root, no Termux, extension center included | 手机本地运行 DeepSeek |
| 24 | lioensky/VCPToolBox | 2403 | JavaScript | 2026-10-25 | 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 |
| 25 | manishiitg/agentworks | 16 | Go | 2026-10-25 | AgentWorks: AI agents that own the work. Goals that chase a metric, and Crews your team asks from Claude, ChatGPT or Cur |
| 26 | ubunatic/harnez | 0 | Go | 2026-10-25 | Open source, repo-first, local-first, cross-agent, AI agent manager, providing guardrails, guidance, templates, telemetr |
| 27 | omnigent-ai/omnigent | 11038 | Python | 2026-10-25 | Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom a |
| 28 | whyihaveyou/dsh-suite | 63 | HTML | 2026-10-25 | The living DeepSeek Harness plugin directory — refreshed hourly, compat-tested daily, with an in-app plugin store and sc |
| 29 | axisvela/praxo-core | 12 | Go | 2026-10-25 | MIT-licensed agent framework for the AxisVela ecosystem: governed agent loop, model/tool/memory/event primitives, plugin |
| 30 | agbossjs/agboss.dev | 1 | JavaScript | 2026-10-25 | Official documentation for AGBoss (https://agboss.dev) — TypeScript framework for mission-critical LangGraph AI agents. |
| 31 | Aayush-Joshi-01/deepcrew-ai | 3 | HTML | 2026-10-25 | Async multi-agent AI library for Python — self-improving agent loops, APEX synthesis, bounded agent spawning, multimodal |
| 32 | daretodave/nexus | 5 | JavaScript | 2026-10-25 | a methodology for autonomous projects that ship themselves (hands off) |
| 33 | agbossjs/agboss | 1 | TypeScript | 2026-10-25 | Spring-style TypeScript framework for mission-critical LangGraph AI agents — @Application DI, Path Scope Flow DSL, trans |
| 34 | iflytek/skillhub | 5287 | Java | 2026-10-25 | Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and au |
| 35 | xujian519/sati | 3 | TypeScript | 2026-10-25 | 面向专利代理人、专利律师与知识产权从业者的桌面端专利智能体 |
| 36 | DJG3DK/persei | 3 | Python | 2026-10-25 | Autonomous coding agent built on LangGraph + deepagents. It natively plans, builds, verifies, and ships real production |
| 37 | neomjs/neo-agent-institution | 11 | JavaScript | 2026-10-25 | Stand up your own cross-model AI engineering team — the way Neo.mjs runs its own. Named AI maintainers with persistent i |
| 38 | pydantic/pydantic-ai | 20861 | Python | 2026-10-25 | How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end |
| 39 | ulsreall/web3-agent-kit | 20 | Python | 2026-10-25 | Open-source toolkit for building AI agents that interact with blockchains — DeFi, restaking, token sniping, portfolio tr |
| 40 | Nucc/spoletta | 0 | Go | 2026-10-25 | Visual builder and engine for agent workflows |
| 41 | laurentftech/pi-outpost | 25 | TypeScript | 2026-10-25 | A self-hosted web interface for pi coding agent. |
| 42 | cccat6/iphone-agent-harness | 8 | C | 2026-10-25 | Automate your real iPhone from Safari with a $2 ESP32. No Mac, no APP, and no jailbreak. Local conversations, your choic |
| 43 | xuxueli/xxl-ai | 51 | Vue | 2026-10-25 | A AI Agent development platform. |
| 44 | HKUDS/nanobot | 49345 | Python | 2026-10-25 | Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi- |
| 45 | trbearth/fieldwork-agent-os | 0 | CSS | 2026-10-25 | Local-first desktop workspace for configurable research agents, cited reports, and optional voice. |
| 46 | eigent-ai/eigent | 15657 | TypeScript | 2026-10-25 | Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex |
| 47 | dryvist/ai-assistant-instructions | 9 | Shell | 2026-10-25 | A comprehensive, vendor-agnostic framework for consistent AI-assisted development workflows - standardized instructions |
| 48 | arcships/rutis | 159 | Rust | 2026-10-25 | A plugin runtime for software that iterates on itself — the substrate where agents write, swap and hot-reload their own |
| 49 | Dr-SoloDev/Lab-solocorp-os2.4 | 0 | Python | 2026-10-25 | Department Architecture for AI agents — every task has an owner. Pre-release: 20 profiles, 9 skills, Central Bus + loop |
| 50 | assafkip/kipi-system | 128 | Python | 2026-10-25 | Your AI brain, externalized. It remembers everything you do, then becomes whatever role you need. Same skeleton can run |
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.