Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
openhuman
Agents & frameworksThe fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
git clone https://github.com/tinyhumansai/openhuman.git -
openbot
Agents & frameworksA local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharing, browser control, and agent-to-agent collaboration.
git clone https://github.com/nightly-labs/openbot.git -
Observer
Agents & frameworksThe orchestrator that deploys micro-agents that monitor anything for you. Running completely locally. Open Source.
git clone https://github.com/Roy3838/Observer.git -
smolvm
Agents & frameworksAn embeddable, portable, branchable virtual machine to safely run Agents locally.
git clone https://github.com/smol-machines/smolvm.git -
starnet
Agents & frameworksA living pixel-art station where real AI agents do real work. Local-first desktop agent harness - bring your own key, watch your crew actually run.
git clone https://github.com/androoAGI/starnet.git -
Agenvoy
Agents & frameworksA local AI agent harness in Go that runs 24/7 with auto-built tools, MCP, and Ollama
git clone https://github.com/pardnchiu/Agenvoy.git -
Meldwork
Agents & frameworksLocal-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.
git clone https://github.com/Ryder-Sun/Meldwork.git -
open-multi-agent
Agents & frameworksSelf-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.
git clone https://github.com/open-multi-agent/open-multi-agent.git -
arcbox
Agents & frameworksRun AI agents on real and isolated machines — own kernel, filesystem, and network — with <100ms boot. Local first, OCI compatible, pure Rust.
git clone https://github.com/arcboxlabs/arcbox.git -
Deepseek-Harness-Local-Android
Agents & frameworksRun the DeepSeek Harness AI agent natively on Android — no root, no Termux, extension center included | 手机本地运行 DeepSeek Agent,免 Root 免 Termux
git clone https://github.com/Soodok/Deepseek-Harness-Local-Android.git -
taracode
Agents & frameworksDevOps & Cloud SI Assistant that runs locally on taraengine for complete privacy.
git clone https://github.com/tara-vision/taracode.git -
local-code-community
Agents & frameworksSource code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Python, Node.js and a shell built into the app.
git clone https://github.com/drawthingsai/local-code-community.git -
forge
Agents & frameworksForge is the open-source runtime for Anthropic's Agent Skills standard — built for the agent that runs next to a service, in your environment, on infrastructure you already operate. Write a SKILL.md. Compile to a portable, hardened agent. Deploy it anywhere containers run: Kubernetes, on-prem, air-gapped, embedded in CI, or as an A2A endpoint.
git clone https://github.com/initializ/forge.git -
HARTOS
Agents & frameworksAn 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.
git clone https://github.com/hertz-ai/HARTOS.git -
munder-difflin
Agents & frameworksan open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions
git clone https://github.com/HarnessMD/munder-difflin.git -
cetus
Agents & frameworksOne macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.
git clone https://github.com/william-jin-cmu/cetus.git -
FABULA-LLM-5
Agents & frameworksA 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.
git clone https://github.com/sergezuber/FABULA-LLM-5.git -
Bittune
Agents & frameworksLocal-first engineering agent that deploys, benchmarks and tunes vLLM/SGLang inference services on your own GPUs, with auditable run evidence.
git clone https://github.com/bitcloud-ai/Bittune.git -
mulmoterminal
Agents & frameworksRun multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you. Local, tmux-backed, MIT.
git clone https://github.com/receptron/mulmoterminal.git -
tasktrooper
Agents & frameworksLocal-first agent platform: board + role agents + agent CLI runs (Claude Code, Cursor, Antigravity, OpenCode) or local and API models (Ollama, LM Studio), all on your own Pc
git clone https://github.com/makifbaysal/tasktrooper.git -
bloks
Agents & frameworksA local-first desktop app for running a team of AI agents on Claude Code, Codex, Cursor, Cline and more, on your own computer.
git clone https://github.com/hamedgitty/bloks.git -
holon
Agents & frameworksOpen-source AI assistants on your own computer or server. Assign tasks, track progress, and let them follow up on ongoing work.
git clone https://github.com/holon-run/holon.git -
kiki
Agents & frameworksOpen-source multi-model AI agent workbench (Desktop GUI, TUI & Web) — dispatch subagents across Claude, GPT, Gemini & Kimi, bridge WeChat/QQ, and run locally.
git clone https://github.com/X-T-E-R/kiki.git -
llama-modchip
Agents & frameworksRun 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).
git clone https://github.com/synchopate/llama-modchip.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.