InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. streamcore-server

    Agents & frameworks

    Open-source realtime voice agent server in Go with WebRTC (WHIP), barge-in, streaming STT/LLM/TTS pipelines, plugin system, multi-language SDKs, SIP telephony, ESP32 support & fully local mode.

    Stale GitHub, streamcoreai 245 ★Apache-2.0Updated 9 days ago

    git clone https://github.com/streamcoreai/streamcore-server.git
  2. Aegis

    Agents & frameworks

    Windows-first desktop oversight for AI agents: live monitoring, local security reviews, token usage, audit reports and opt-in action policies/MCP gateways. Experimental Hyper-V guest execution; macOS/Linux experimental.

    Stale GitHub, antropos17 158 ★MITUpdated 20 days ago

    git clone https://github.com/antropos17/Aegis.git
  3. 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
  4. tma1

    Agents & frameworks

    Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.

    Stale GitHub, tma1-ai 122 ★Apache-2.0Updated 17 days ago

    git clone https://github.com/tma1-ai/tma1.git
  5. sheprd

    Agents & frameworks

    Native client for Herdr on macOS, Linux, and Windows, built with Rust and GPUI. View terminal sessions, workspaces, Git worktrees, and agent activity through your local Herdr daemon.

    Indexed GitHub, sheprd-labs 2,306 ★Apache-2.0Updated today

    git clone https://github.com/sheprd-labs/sheprd.git
  6. Hypha

    Agents & frameworks

    Harness-oriented agent system framework for production-grade LLM agent applications

    Indexed GitHub, CodeSoul-co 452 ★Apache-2.0Updated yesterday

    git clone https://github.com/CodeSoul-co/Hypha.git
  7. Agentlas-OS

    Agents & frameworks

    The Open-Source AI Agent OS inspired by OpenAI Dots, Meta Muse, OpenClaw, Hermes & Mem0. Autonomous 3-tier headhunting, Receipt & Verifier loops, scoped memory, and BYOM for Claude Code, Codex & Cursor.

    Indexed GitHub, agentlas-ai 1,459 ★Apache-2.0Updated yesterday

    git clone https://github.com/agentlas-ai/Agentlas-OS.git
  8. Vibelution

    Agents & frameworks

    Local-first AI agent workbench: research teams that plan, build and review together, a finance agent, and virtual human companions — in one Electron desktop app.

    Stale GitHub, CCDawn 79 ★MITUpdated 9 days ago

    git clone https://github.com/CCDawn/Vibelution.git
  9. captain-claw

    Agents & frameworks

    Command a fleet of AI agents, on every deck, every desk, every wrist. Self-hosted multi-agent platform with memory, a coding pipeline, Flows, a team kiosk and voice devices. Any LLM, or 100% local with Ollama.

    Indexed GitHub, kstevica 196 ★MITUpdated yesterday

    git clone https://github.com/kstevica/captain-claw.git
  10. FABULA-LLM-5

    Agents & frameworks

    A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every green run leaves a receipt anyone can replay. Built for one small model on one machine (LM Studio, MLX) or any OpenAI-compatible endpoint. No telemetry. macOS · Linux · Windows.

    Stale GitHub, sergezuber 82 ★MITUpdated 55 days ago

    git clone https://github.com/sergezuber/FABULA-LLM-5.git
  11. rag-from-scratch

    Agents & frameworks

    Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.

    Stale GitHub, pguso 1,643 ★MITUpdated 8 months ago

    git clone https://github.com/pguso/rag-from-scratch.git
  12. llama-modchip

    Agents & frameworks

    Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).

    Indexed GitHub, synchopate 1,137 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/synchopate/llama-modchip.git
  13. SztuCode

    Agents & frameworks

    An experimental playground for open-source, all-in-one office AI for universities: code, docs, spreadsheets, slides, browser – all are the AI's workspace. Local-first, event-driven, auditable, with both TypeScript and Python implementations.

    Stale GitHub, rojim666 110 ★MITUpdated 5 days ago

    git clone https://github.com/rojim666/SztuCode.git
  14. madre

    Agents & frameworks

    MADRE · Codex, Claude Code, Gemini CLI and OpenCode in one local chat on your machine, with one memory every agent shares. Home for all your projects and a Coordinator above them. Read-only by default; you unlock more per message. In Spanish and English. Public beta.

    Stale GitHub, jossuealcacao-exe 122 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/jossuealcacao-exe/madre.git
  15. augur

    Agents & frameworks

    🦉 Augur — 本地优先的投资研究记忆系统:18 位投资大师独立分析 + 加权共识,证据带时间语义、每次运行可复查,CLI / Dashboard / MCP。A local-first research memory system with 18 investor personas.

    Stale GitHub, BruceLanLan 650 ★MITUpdated 18 days ago

    git clone https://github.com/BruceLanLan/augur.git
  16. ShibaClaw

    Agents & frameworks

    Self-hosted personal AI agent with a WebUI, memory, tools, MCP, sub-agents and automations. Connect local or cloud LLMs.

    Indexed GitHub, RikyZ90 85 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/RikyZ90/ShibaClaw.git
  17. my-virtual-office

    Agents & frameworks

    A self-hosted 2D AI workspace for AI Agents

    Indexed GitHub, eliautobot 375 ★AGPL-3.0Updated 2 days ago

    git clone https://github.com/eliautobot/my-virtual-office.git
  18. sugar

    Agents & frameworks

    Mission control for your agent fleet. One local-first board for Claude Code, Codex, Goose, Cursor and any MCP harness: durable tasks, live activity, cost attribution and audit exports.

    Stale GitHub, roboticforce 100 ★Custom licence (see repository)Updated 6 days ago

    git clone https://github.com/roboticforce/sugar.git
  19. kiki

    Agents & frameworks

    Open-source multi-model AI agent workbench (Desktop GUI, TUI & Web) — dispatch subagents across Claude, GPT, Gemini & Kimi, bridge WeChat/QQ, and run locally.

    Indexed GitHub, X-T-E-R 56 ★MITUpdated today

    git clone https://github.com/X-T-E-R/kiki.git
  20. willdeep-cli

    Agents & frameworks

    自托管 AI Coding Agent(Rust):常驻 Runtime 撑起终端 / 浏览器 / 手机三端;每行改动可追溯到具体 Agent 与工具调用,子 Agent 的活由退出码裁决,检查点回退、目标 token 预算与验收清单跨轮次跨重启累计,用量与反馈账本留在本地。接任意 OpenAI 兼容或 Anthropic 端点。Self-hosted auditable AI coding agent: per-line attribution, exit-code-verified sub-agents, restart-safe goal budgets, local usage and feedback ledgers.

    Indexed GitHub, niuwoai 201 ★Custom licence (see repository)Updated today

    git clone https://github.com/niuwoai/willdeep-cli.git
  21. myPKA

    Agents & frameworks

    AI-powered Personal Knowledge Assistance in a folder. Built on the ICOR methodology. Plain markdown. Any LLM. Yours forever.

    Stale GitHub, myICOR 319 ★MITUpdated 14 days ago

    git clone https://github.com/myICOR/myPKA.git
  22. Apeireth

    Agents & frameworks

    Apeireth — a digital companion that grows with you. Pure Safe Rust AGI cognitive microkernel: memory that fades like a person's, human approval before every side effect, honest boundaries. 31-member workspace (30 crates + 1 bench).

    Indexed GitHub, Apeireth 371 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/Apeireth/Apeireth.git
  23. HARTOS

    Agents & frameworks

    An AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-compatible. Boots, has its own Wayland compositor, and runs on 8GB. Apache 2.0.

    Indexed GitHub, hertz-ai 52 ★Apache-2.0Updated today

    git clone https://github.com/hertz-ai/HARTOS.git
  24. Sidekick

    Agents & frameworks

    A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

    Stale GitHub, johnbean393 3,320 ★MITUpdated 47 days ago

    git clone https://github.com/johnbean393/Sidekick.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.