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: 2026-09-06 20:30 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | Lykhoyda/rn-dev-agent | 11 | TypeScript | 2026-09-06 | Claude Code | Codex plugin for React Native — explores codebases, designs architecture, implements features and QA the c |
| 2 | HarnessRouter/harnessrouter | 666 | Python | 2026-09-06 | HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run C |
| 3 | wmcmahan/cycgraph | 2 | TypeScript | 2026-09-06 | Agent context compressor and memory persistent orchestration |
| 4 | ag2ai/ag2 | 4907 | Python | 2026-09-06 | AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x |
| 5 | ellmos-ai/bach | 7 | Python | 2026-09-06 | BACH v3.13.0-bluesky: local-first text-based OS for LLM agents with SQLite memory, 113+ handlers, 550+ tools, MCP server |
| 6 | linny006/agent-framework-radar | 6 | Python | 2026-09-06 | Live index of the newest agent frameworks shipping on GitHub, sorted by recency not stars |
| 7 | openamer/openamer | 5 | Python | 2026-09-06 | The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System |
| 8 | macanderson/context-graph-protocol | 1 | Rust | 2026-09-06 | The Context Graph Protocol is an open wire protocol for context retrieval. It treats a piece of context as a typed, budg |
| 9 | CarlosCaPe/octorato | 15 | Python | 2026-09-06 | Open-source AI agent operating system: one file-native brain (230+ skills, 160+ specialist agents) run across many seale |
| 10 | tinyhumansai/tinyhivemind | 1 | Rust | 2026-09-06 | Hive mind mechanics for agents. A step closer towards AGI |
| 11 | 10xHub/agentflow-docs | 2 | TypeScript | 2026-09-06 | Official documentation for Agentflow, built with Docusaurus and structured via the Divio system: tutorials, how-to guide |
| 12 | 10xHub/agentflow-cli | 5 | Python | 2026-09-06 | FastAPI server and CLI for Agentflow. Auto-generates a REST API from your agent graph, with JWT/custom auth, RBAC author |
| 13 | JKHeadley/instar | 77 | TypeScript | 2026-09-06 | Persistent Claude Code agents with scheduling, sessions, memory, and Telegram. |
| 14 | devoidfury/hotdog | 14 | TypeScript | 2026-09-06 | AI agent with zero dependencies, bring your own bun |
| 15 | Ethanon/developer.ai | 9 | Shell | 2026-09-06 | Lifecycle-shaped Claude Code agent kit: scheduled audits → ready-state issues → developer-agent PRs → multi-persona advi |
| 16 | israriqbal/agent-ecologies | 120 | HTML | 2026-09-06 | Ultimate Multi-Agent OS for Autonomous AI NPCs 2026 |
| 17 | Losina24/ARCH | 4 | TypeScript | 2026-09-06 | ARCH (Autonomous Requirements-to-Code Hierarchy) is a terminal application that translates user requirements into a visu |
| 18 | tya5/reyn | 10 | Python | 2026-09-06 | AI agent workflow OS . Constrained, validated, replayable execution. Predictability over autonomy. |
| 19 | plaited/plaited | 10 | TypeScript | 2026-09-06 | Framework for sovereign agent nodes, A2A modnets, generative UI, and behavioral runtime provenance. |
| 20 | rekursiv-ai/sagent | 32 | Python | 2026-09-06 | A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool cal |
| 21 | dshakes/lantern | 0 | TypeScript | 2026-09-06 | Production runtime for AI agents — run the whole stack locally with one command, ship to your own cloud. Real WhatsApp/S |
| 22 | kirklasalle/orrery | 1 | Python | 2026-09-06 | Stateful multi-tier cognitive cycles for long-horizon agents. Governance claims are CI-enforced: the build fails if the |
| 23 | assafkip/kipi-system | 109 | Python | 2026-09-06 | Your AI brain, externalized. It remembers everything you do, then becomes whatever role you need. Same skeleton can run |
| 24 | yuanchuzi2026/silicon-garden | 1 | HTML | 2026-09-06 | 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。 |
| 25 | omnigent-ai/omnigent | 9744 | Python | 2026-09-06 | Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom a |
| 26 | AndersonBY/vv-agent | 1 | Python | 2026-09-06 | A lightweight agent framework for production runtime. Cycle-based execution with pluggable LLM backends, tool dispatch, |
| 27 | alpercodes/alms | 4 | Rust | 2026-09-06 | Rust multi-agent coordination platform: HTTP/SSE gateway, agent runtime with token-budgeted context, per-tool sandboxing |
| 28 | whyihaveyou/dsh-suite | 52 | HTML | 2026-09-06 | The living DeepSeek Harness plugin directory — refreshed hourly, compat-tested daily, with an in-app plugin store and sc |
| 29 | abdra7/Lycosa | 0 | Python | 2026-09-06 | Lycosa — Open-source AI agent orchestration platform for building, coordinating, and deploying multi-agent LLM systems w |
| 30 | manishiitg/coding-agent-loop | 13 | Go | 2026-09-06 | AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company. |
| 31 | footprintjs/agentfootprint | 20 | TypeScript | 2026-09-06 | Context engineering, abstracted. Build AI agents whose every LLM call traces back to what was injected, who triggered it |
| 32 | daniel06s6995/deepseek-harness-software-OPC | 0 | JavaScript | 2026-09-06 | Transform DeepSeek Harness into a software company with 13 specialist departments, visualized on a live dashboard for re |
| 33 | Pericardiac-podzolsoil527/deepseek-plugin-store | 0 | — | 2026-09-06 | 发现、安装 DeepSeek Harness 生态中的社区插件、工具与扩展，探索 1493+ 精选主题插件并实时更新目录。 |
| 34 | yangheng95/opencorvus | 162 | TypeScript | 2026-09-06 | Your own agentic working mate. For long horizon and complex task automation |
| 35 | Aureliedumbfounding630/agent-governance-toolkit | 0 | — | 2026-09-06 | Manage and monitor AI agents in production environments with tools for governance, safety, and compliance. |
| 36 | Akagilnc/ak-pi-workflow-roles | 1 | TypeScript | 2026-09-06 | A governance layer for AI coding work — not an orchestrator. Seven gated roles with typed submissions, independent audit |
| 37 | mcheemaa/mistri | 18 | Ruby | 2026-09-06 | The agent harness for Ruby applications. Durable sessions, streaming, human-in-the-loop approval, compaction, structured |
| 38 | IkhsanMAlbar/govchain-llm-orchestrator | 0 | HTML | 2026-09-06 | Governance-Driven AI Development Framework 2026: Enforce Conventions, Quality Gates & Domain Expertise |
| 39 | Smita6756/Hbrain | 0 | Python | 2026-09-06 | Orchestrate multiple AI specialists to process one query in parallel and generate a single integrated concept. |
| 40 | carlososoriopulgar/agent-kernel | 0 | — | 2026-09-06 | Manage durable agent memory using a simple markdown workspace with inspectable files instead of complex frameworks. |
| 41 | peruzzo3265/ClawTrap | 0 | JavaScript | 2026-09-06 | Play an agent-native maze game where an AI uses your local files and memory to build traps and challenge your survival. |
| 42 | adaxial-lineofscrimmage6998/mempalace | 1 | — | 2026-09-06 | Manage AI memories with a lightweight, local-first SQLite binary. Replaces heavy dependencies with a fast, single-file t |
| 43 | berrettabadger966/genesis-pantheon | 2 | Python | 2026-09-06 | Build a production-grade multi-agent AI framework for collaborative software development with clean orchestration and re |
| 44 | LovaHuguel/Khala-Orchestrator-Core | 1 | HTML | 2026-09-06 | 🤖 AI Agent Teams 2026: Build & Deploy Autonomous AI Systems 🚀 |
| 45 | vmy41/agent-harness | 1 | — | 2026-09-06 | Build coding agents with a clean-room harness for streaming loops, tool control, session save, secure creds, and layered |
| 46 | skerry699/agent-symphony | 120 | HTML | 2026-09-06 | Multi-Agent AI Task Orchestrator 2026 |
| 47 | Ansellwaxlike187/cowork-semantic-search | 0 | Python | 2026-09-06 | Search your local documents with semantic search in any MCP client, no API keys, no cloud access |
| 48 | fathirn6263/harness-engineering | 0 | — | 2026-09-06 | Learn Harness Engineering with notes, concepts, and hands-on practice for building AI agent workflows and constraint-dri |
| 49 | JdominguezEcommium/agentic-self-regulation-loop | 0 | HTML | 2026-09-06 | 2026 AI Agent Loop v2.0: Autonomous Coding with Guardrails & Self-Healing |
| 50 | 111nathanlar/Agent-Worlds | 1 | HTML | 2026-09-06 |
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.