InnerVault

Library

87,246 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. smolagents

    Agents & frameworks

    Hugging Face's small agent library, where agents act by writing and running Python code.

    Hand-checked InnerVault (hand-checked), Hugging Face Apache-2.0

    pip install "smolagents[toolkit]"
  2. mobius

    Agents & frameworks

    möbius is a small, frontend-neutral Rust framework for coding agents.

    Indexed GitHub, citizenhicks 620 ★Apache-2.0Updated today

    git clone https://github.com/citizenhicks/mobius.git
  3. ai-employees

    Agents & frameworks

    Open 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.

    Indexed GitHub, markfulton 899 ★MITUpdated 2 days ago

    git clone https://github.com/markfulton/ai-employees.git
  4. tinyagents

    Agents & frameworks

    A small, provider-neutral agent harness written in Rust

    Indexed GitHub, tinyhumansai 135 ★GPL-3.0Updated 4 days ago

    git clone https://github.com/tinyhumansai/tinyagents.git
  5. automatos-ai

    Agents & frameworks

    The 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.

    Indexed GitHub, AutomatosAI 79 ★Apache-2.0Updated yesterday

    git clone https://github.com/AutomatosAI/automatos-ai.git
  6. phil

    Agents & frameworks

    Phil 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.

    Indexed GitHub, bennyjo 253 ★Apache-2.0Updated today

    git clone https://github.com/bennyjo/phil.git
  7. WEIPING_WHALE

    Agents & frameworks

    A 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.

    Stale GitHub, appleweiping 131 ★MITUpdated 24 days ago

    git clone https://github.com/appleweiping/WEIPING_WHALE.git
  8. 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 609 ★MITUpdated yesterday

    git clone https://github.com/qybaihe/mu.git
  9. agenticow

    Agents & frameworks

    Git for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory (83x faster, 3000x smaller snapshots)

    Stale GitHub, ruvnet 56 ★MITUpdated 7 days ago

    git clone https://github.com/ruvnet/agenticow.git
  10. mulmoclaude

    Agents & frameworks

    Nurture 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.

    Stale GitHub, receptron 386 ★MITUpdated 11 days ago

    git clone https://github.com/receptron/mulmoclaude.git
  11. dsh-sieve

    Agents & frameworks

    dsh-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。

    Stale GitHub, Sev7eEn7 110 ★MITUpdated 17 days ago

    git clone https://github.com/Sev7eEn7/dsh-sieve.git
  12. 5dive

    Agents & frameworks

    Run 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.

    Indexed GitHub, 5dive-ai 121 ★MITUpdated today

    git clone https://github.com/5dive-ai/5dive.git
  13. 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 57 days ago

    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.