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: 2026-08-02 15:45 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | MariusYvard/corparius | 0 | Python | 2026-08-02 | Self-hosted framework for autonomous AI micro-companies. Describe a business in plain language and corparius runs it as |
| 2 | danmo-ai/danmo-work | 2 | Go | 2026-08-02 | Open-source AI Work Agent — coding-agent-grade loop for long-horizon work: code, docs, slides, sheets, MCP & IM on one t |
| 3 | manishiitg/coding-agent-loop | 8 | Go | 2026-08-02 | AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company. |
| 4 | PiyotaHu/Voxa | 1 | Rust | 2026-08-02 | Rust-native real-time multimodal agent runtime with bounded graph execution and safe Rust, C++, Python, and TypeScript n |
| 5 | jiayan-xu/agent-core | 1 | Rust | 2026-08-02 | Enterprise-grade AI agent engine. Lightweight, secure, MCP-native. Built in Rust. |
| 6 | esengine/DeepSeek-Reasonix | 28872 | Go | 2026-08-02 | DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running. |
| 7 | RNT56/ThinClaw | 0 | Rust | 2026-08-02 | Self-hosted, privacy-first AI collaborator with durable memory, real tools, channel-native access, routines, and auditab |
| 8 | Omni-Craft/OmniCraft | 1 | Python | 2026-08-02 | OmniCraft — meta-harness open-source para todos os seus agentes de IA (pt-BR). Chat · Code · Craftwork. |
| 9 | streamcoreai/streamcore-server | 80 | Go | 2026-08-02 | Open-source realtime voice agent server in Go with WebRTC (WHIP), barge-in, streaming STT/LLM/TTS pipelines, plugin syst |
| 10 | Rakshit64w43/agent-gateway-hub | 2 | HTML | 2026-08-02 | 🚀 Opendray v2 2026 – Universal AI Agent Gateway (Slack, Telegram, Discord, DingTalk) |
| 11 | linny006/agent-framework-radar | 1 | Python | 2026-08-02 | Live index of the newest agent frameworks shipping on GitHub, sorted by recency not stars |
| 12 | phamvanquyit/raw-agents | 2 | TypeScript | 2026-08-02 | Self-hosted AI agents with a web UI — extend with Python/JS tools & MCP, schedule with cron Jobs, publish as public chat |
| 13 | IkhsanMAlbar/govchain-llm-orchestrator | 0 | HTML | 2026-08-02 | Governance-Driven AI Development Framework 2026: Enforce Conventions, Quality Gates & Domain Expertise |
| 14 | tya5/reyn | 7 | Python | 2026-08-02 | AI agent workflow OS . Constrained, validated, replayable execution. Predictability over autonomy. |
| 15 | RyanAlberts/best-of-Agent-Harnesses | 444 | Python | 2026-08-02 | 🏆 Curated, ranked list of AI agent harnesses (100+) — plus an MCP server, llms.txt & JSON so agents can recommend them t |
| 16 | LovaHuguel/Khala-Orchestrator-Core | 1 | HTML | 2026-08-02 | 🤖 AI Agent Teams 2026: Build & Deploy Autonomous AI Systems 🚀 |
| 17 | israriqbal/agent-ecologies | 154 | HTML | 2026-08-02 | Ultimate Multi-Agent OS for Autonomous AI NPCs 2026 |
| 18 | hertz-ai/HARTOS | 49 | Python | 2026-08-02 | An AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-comp |
| 19 | Marssssss/OneAI | 37 | Rust | 2026-08-02 | A cross-platform agent framework and samples, support on Windows/MacOS/Android/iOS/HarmonyOS |
| 20 | 111nathanlar/Agent-Worlds | 1 | HTML | 2026-08-02 | |
| 21 | JdominguezEcommium/agentic-self-regulation-loop | 0 | HTML | 2026-08-02 | 2026 AI Agent Loop v2.0: Autonomous Coding with Guardrails & Self-Healing |
| 22 | Bande-a-Bonnot/Boucle-framework | 120 | Shell | 2026-08-02 | Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it |
| 23 | agentjido/jidoka | 32 | Elixir | 2026-08-02 | Developer-friendly LLM agent harness built on Jido and Jido AI |
| 24 | qadeer-ux/oh-my-codex-remix | 1 | HTML | 2026-08-02 | 🧠 Ultimate AI Coding Agent 2026: Supercharge Your Dev Workflow for Faster, Cleaner Code |
| 25 | HKUDS/nanobot | 46514 | Python | 2026-08-02 | Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi- |
| 26 | griffinwork40/agent-afk | 46 | TypeScript | 2026-08-02 | Start a run in your terminal and walk away. Get pinged when it finishes, or needs you. Every step is a readable trace yo |
| 27 | Aureliolo/synthorg | 9 | Python | 2026-08-02 | SynthOrg - Framework for building synthetic organizations with autonomous AI agents |
| 28 | agentscope-ai/agentscope-java | 4846 | Java | 2026-08-02 | Build distributed, production-grade, long-running agents. |
| 29 | api-evangelist/autogen-studio | 0 | — | 2026-08-02 | AutoGen Studio — Microsoft no-code GUI for building multi-agent AutoGen workflows |
| 30 | joseym/salvor | 1 | Rust | 2026-08-02 | An event-sourced runtime for AI agents that survives kill -9, written in Rust. |
| 31 | brandonkindred/Khala-Agentic-AI-Teams | 5 | Python | 2026-08-02 | Many Agents, one objective... yours |
| 32 | skerry699/agent-symphony | 154 | HTML | 2026-08-02 | Multi-Agent AI Task Orchestrator 2026 |
| 33 | agenvoy/Agenvoy | 364 | Go | 2026-08-02 | Make AI actually work for you - A personal agent that writes its own tools and repairs itself. |
| 34 | Spitfire-Products/nexus-cortex | 0 | TypeScript | 2026-08-02 | A headless, multi-provider AI agent harness — embed it as a library, script it from the CLI, or run it as a stateful age |
| 35 | exha1078/agentic-workflow-orchestrator | 1 | HTML | 2026-08-02 | 🚀 GenAI Agents Production Blueprint 2026: Code-First Enterprise Deployment |
| 36 | nguyenquoaca-hash/agentic-mesh | 2 | HTML | 2026-08-02 | Multi-Agent AI Orchestrator 2026 🚀 | YAML, 6+ LLM Providers, ReAct & Swarm |
| 37 | ChaoYue0307/awesome-graph-engineering | 17 | Python | 2026-08-02 | 🕸️ Engineer the organization, not just the agent. 558 curated resources · 9 design layers · 11 sections · 250 papers & p |
| 38 | parkerluxu/Awesome-agent-cases | 2 | — | 2026-08-02 | A bilingual, continuously updated directory of AI agent cases, news, open-source projects, papers, and reusable resource |
| 39 | Ikalus1988/MisakaNet | 365 | Python | 2026-08-02 | 📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging |
| 40 | dryvist/ai-assistant-instructions | 9 | Shell | 2026-08-02 | A comprehensive, vendor-agnostic framework for consistent AI-assisted development workflows - standardized instructions |
| 41 | substructureai/substructure | 5 | Rust | 2026-08-02 | Substructure is an open-source engine that drives your agent loop with JSON webhooks. It keeps sessions durable and stre |
| 42 | bailong-Hakuryu/E.R.I.I | 1 | Python | 2026-08-02 | A decoupled, zero-dependency dual-track long-term memory engine for LLM AI Agents. | 经验回想与印象整合引擎 |
| 43 | shimo4228/contemplative-agent | 5 | Python | 2026-08-02 | Contemplative Agent (CA) — an autonomous agent that carries an explicit, human-editable constitution and amends it. Ever |
| 44 | rundesk-ai/rundesk-cli | 1 | Python | 2026-08-02 | Persistent self-improving AI teammates with memory, skills, and schedules. |
| 45 | JKHeadley/instar | 75 | TypeScript | 2026-08-02 | Persistent Claude Code agents with scheduling, sessions, memory, and Telegram. |
| 46 | tsingxuanhan/NexusFlow | 0 | Python | 2026-08-02 | 面向超长程复杂任务的群体智能引擎 | CDoL认知分工 | 端边云三层架构 | 10-Agent协作 |
| 47 | trbearth/fieldwork-agent-os | 0 | CSS | 2026-08-02 | Local-first desktop workspace for configurable research agents, cited reports, and optional voice. |
| 48 | jycicy/minicode | 1 | Python | 2026-08-02 | 基于 Claude Code 架构精简的 AI Agent 框架 | 7层架构 Agentic Loop + 6个内置工具 + 三级权限控制 + 动态System Prompt | 可以更加详细的学习工程级架构,也可以自定义内置工具使用 |
| 49 | pamod-madubashana/cotrex-ai | 1 | Rust | 2026-08-02 | Cotrex is an open-source AI execution engine that enables LLMs to securely use tools, execute tasks, and automate real-w |
| 50 | omnigent-ai/omnigent | 8030 | Python | 2026-08-02 | Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom a |
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.