Library
87,246 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
smolagents
Agents & frameworksHugging Face's small agent library, where agents act by writing and running Python code.
pip install "smolagents[toolkit]" -
mobius
Agents & frameworksmöbius is a small, frontend-neutral Rust framework for coding agents.
git clone https://github.com/citizenhicks/mobius.git -
ai-employees
Agents & frameworksOpen source AI Employees. 8 scheduled business roles, 60 routines, on Claude Code and 10 other harnesses. They drive your browser the way you do and improve every run. You own the files.
git clone https://github.com/markfulton/ai-employees.git -
tinyagents
Agents & frameworksA small, provider-neutral agent harness written in Rust
git clone https://github.com/tinyhumansai/tinyagents.git -
automatos-ai
Agents & frameworksThe open-source AI Operating System — run a workforce of AI agents on your own machine. Any model, 1,000+ tools, a Knowledge Graph, and your own Claude Code as agents. Self-host with docker compose.
git clone https://github.com/AutomatosAI/automatos-ai.git -
phil
Agents & frameworksPhil is a self-improving trader: an AI agent that trades short-term prediction markets and rewrites his own strategy after every settled bet. Paper 24/7 in the cloud; small capped real stakes via Pearl Connect.
git clone https://github.com/bennyjo/phil.git -
WEIPING_WHALE
Agents & frameworksA small terminal coding agent for DeepSeek models: it reads your repository, runs commands after asking, proposes edits as patches you apply, and checkpoints the workspace around every turn so any turn can be undone.
git clone https://github.com/appleweiping/WEIPING_WHALE.git -
mu
Agents & frameworksmu (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.
git clone https://github.com/qybaihe/mu.git -
agenticow
Agents & frameworksGit for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory (83x faster, 3000x smaller snapshots)
git clone https://github.com/ruvnet/agenticow.git -
mulmoclaude
Agents & frameworksNurture your own AI assistant on your own computer. Local-first and MIT: memories, data and apps stay as plain files in your workspace. Chat summons the right GUI — wiki, spreadsheet, chart, form, 3D. Build small apps for an audience of one, no programming required.
git clone https://github.com/receptron/mulmoclaude.git -
dsh-sieve
Agents & frameworksdsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。
git clone https://github.com/Sev7eEn7/dsh-sieve.git -
5dive
Agents & frameworksRun your own AI team from your phone. Claude Code, Codex and more on your own server: shared tasks, always-on agents, a small composable bash core. MIT. An open-source alternative to Grok Bot and OpenAI Dots.
git clone https://github.com/5dive-ai/5dive.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
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.