InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

Looks like a goal we have a starting path for: I want to build an AI agent

  1. cleancode

    Agents & frameworks

    Canvas for orchestrating Claude Code, Codex, and CLI agents in parallel. Delegate tasks and build reusable AI workflows.

    Indexed GitHub, chen-985211 114 ★MITUpdated today

    git clone https://github.com/chen-985211/cleancode.git
  2. awesome-hermes-agent-zh

    Agents & frameworks

    Hermes Agent中文站- 中文实战入口:上手路径、国内落地、OpenClaw 共存迁移、排障参考与可下载方案包。

    Stale GitHub, zcweah1981 56 ★Updated 7 days ago

    git clone https://github.com/zcweah1981/awesome-hermes-agent-zh.git
  3. harness

    Agents & frameworks

    Run fleets of parallel coding agents with governance — Rust control plane for Claude Code & Codex: orchestration, policy, cross-agent review, observability.

    Indexed GitHub, majiayu000 92 ★MITUpdated yesterday

    git clone https://github.com/majiayu000/harness.git
  4. LLM-PySC2

    Agents & frameworks

    LLM-PySC2 is NKAI Decision Team and NUDT Decision Team's Python component of the StarCraft II LLM Decision Environment. It exposes Deepmind's PySC2 Learning Environment API as a Python LLM Environment.

    Stale GitHub, NKAI-Decision-Team 162 ★Apache-2.0Updated 19 months ago

    git clone https://github.com/NKAI-Decision-Team/LLM-PySC2.git
  5. bothouse

    Agents & frameworks

    把 Claude Code、Codex、Gemini 拉进一个群,组长 AI 分活,大家共用一份记忆。| Put Claude Code, Codex and Gemini CLI in one Discord group: a team-lead AI splits the work, and they share one memory.

    Indexed GitHub, zuiho-kai 231 ★Apache-2.0Updated today

    git clone https://github.com/zuiho-kai/bothouse.git
  6. agentdb

    Agents & frameworks

    Vector memory that gets smarter every time your agent uses it.

    Stale GitHub, ruvnet 97 ★MITUpdated 5 days ago

    git clone https://github.com/ruvnet/agentdb.git
  7. opus-manager

    Agents & frameworks

    Make Claude the manager, not the coder: one skill that hands work to cheaper AI CLIs, verifies the results, and gets a second vendor to review.

    Indexed GitHub, yanauto 63 ★MITUpdated yesterday

    git clone https://github.com/yanauto/opus-manager.git
  8. wenflow

    Agents & frameworks

    先说清你想解决的事,再开始学习。问流 WenFlow:从真实问题出发的开源 AI 学习路径原型——对话澄清目标、生成可执行路径、回合式教学、遗忘曲线复习、学习负荷追踪(LSS/KTL/LF/LSB);自带 18 页管理后台与虚拟学习者仿真。Vue3 + Node.js + SQLite,MIT,可自托管。早期实验原型。

    Stale GitHub, wenflow-org 68 ★MITUpdated 4 days ago

    git clone https://github.com/wenflow-org/wenflow.git
  9. platypus

    Agents & frameworks

    Self-hosted AI Agents for your whole team — on your infrastructure, your models, around the clock.

    Indexed GitHub, willdady 130 ★MITUpdated yesterday

    git clone https://github.com/willdady/platypus.git
  10. Clouds-Coder

    Agents & frameworks

    Clouds Coder is a local-first coding agent platform centered on separating the CLI execution plane from the Web user plane, with Web UI, Skills Studio, resilient streaming, and long-task recovery controls.

    Stale GitHub, FonaTech 288 ★MITUpdated 17 days ago

    git clone https://github.com/FonaTech/Clouds-Coder.git
  11. markus

    Agents & frameworks

    The all-in-one AI workforce platform, to build AI agent teams. You are the boss.

    Indexed GitHub, markus-global 218 ★Apache-2.0Updated yesterday

    git clone https://github.com/markus-global/markus.git
  12. clodex

    Agents & frameworks

    A visual manager for fleets of Claude Code, Codex and Muse agents — real terminals, agents that message each other, teams that run tickets on worktrees, across your Mac and any Linux box.

    Indexed GitHub, avirtual 138 ★Apache-2.0Updated yesterday

    git clone https://github.com/avirtual/clodex.git
  13. open-dynamic-workflows

    Agents & frameworks

    Open Dynamic Workflows: TypeScript CLI runtime for Claude Code-style dynamic workflows across Codex, Claude Code, Gemini, Qwen, Kimi, and custom coding-agent CLIs.

    Stale GitHub, xz1220 111 ★MITUpdated 28 days ago

    git clone https://github.com/xz1220/open-dynamic-workflows.git
  14. preference-lab

    Agents & frameworks

    Policy-driven preference data for content moderation, with source-linked evidence, resumable runs, budget controls and TRL/ShareGPT exports.

    Stale GitHub, dengxianghua888-ops 50 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/dengxianghua888-ops/preference-lab.git
  15. axion1_0

    Agents & frameworks

    Frontier-level agent capabilities with nothing more than high-quality data and a simple training recipe: 2 SFT + RL, no mid-training/DPO/OPD. Full recipe released.

    Stale GitHub, bytedance 70 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/bytedance/axion1_0.git
  16. SOLiD

    Agents & frameworks

    SOTA LiDAR & 4D Radar Place Recognition + Online Loop Closing / Multi-session SLAM for ROS 1/2 (IEEE RA-L'24 w/ ICRA'25)

    Stale GitHub, sparolab 212 ★BSD-3-ClauseUpdated 6 days ago

    git clone https://github.com/sparolab/SOLiD.git
  17. deskfolk

    Agents & frameworks

    Open source alternative for Grok Bot/Muse/Dots + Codex/Claude GUI. Preserve better UI/UX with better performance

    Indexed GitHub, Blackman99 56 ★MITUpdated yesterday

    git clone https://github.com/Blackman99/deskfolk.git
  18. walrus-memory

    Agents & frameworks

    A portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.

    Stale GitHub, MystenLabs 132 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/MystenLabs/walrus-memory.git
  19. PumpGrok

    Agents & frameworks

    1-Click Grok Bot 8 Man Crypto Trading Desk as seen on X

    Stale GitHub, swcstudiospace 55 ★AGPL-3.0Updated 6 days ago

    git clone https://github.com/swcstudiospace/PumpGrok.git
  20. hunter-community

    Agents & frameworks

    HunterCode · Community Edition · 腾讯 WorkBuddy 金融版的开源本地替代方案 · open-source, local alternative to Tencent WorkBuddy Finance Edition · 多智能体投研终端 A股/港股/美股 · 推理在你机器上跑 · 仓位不出你硬盘 · BYOK · Apache 2.0 · docker compose 自托管

    Indexed GitHub, agentpit-io 612 ★Apache-2.0Updated today

    git clone https://github.com/agentpit-io/hunter-community.git
  21. mu

    Agents & frameworks

    mu (μ): most of what a coding agent decides isn't code. mu hands 40 kinds of yes/no calls to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi.

    Indexed GitHub, qybaihe 607 ★MITUpdated yesterday

    git clone https://github.com/qybaihe/mu.git
  22. agency-orchestrator

    Agents & frameworks

    🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 276 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 15 LLM providers (11 key-free). 一句话组建你的「一人公司」AI 专家团队,几分钟交付完整方案;验收自动核验,网页 / 桌面 / Docker 全渠道。

    Stale GitHub, jnMetaCode 2,435 ★Apache-2.0Updated 13 days ago

    git clone https://github.com/jnMetaCode/agency-orchestrator.git
  23. aiquant-lite

    Agents & frameworks

    AI 原生 A 股投研中枢|百万级本地数据 × 量化实验 × 多模型研究 × 可追溯决策。Research deeper. Decide with evidence. · Local-first · Hermes / MCP.

    Stale GitHub, Shixi216 53 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/Shixi216/aiquant-lite.git
  24. mulmoterminal

    Agents & frameworks

    Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you. Local, tmux-backed, MIT.

    Stale GitHub, receptron 263 ★MITUpdated 6 days ago

    git clone https://github.com/receptron/mulmoterminal.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.