InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. graphai

    Agents & frameworks

    GraphAI is an asynchronous data flow execution engine, which allows developers to build agentic applications by describing agent workflows as declarative data flow graphs in YAML or JSON.

    Indexed GitHub, receptron 375 ★MITUpdated 3 days ago

    git clone https://github.com/receptron/graphai.git
  2. agentdescent

    Agents & frameworks

    Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.

    Indexed GitHub, ThinkFlowLab 221 ★MITUpdated today

    git clone https://github.com/ThinkFlowLab/agentdescent.git
  3. deepresearch-agent

    Agents & frameworks

    一个生产级的深度研究 Agent 系统,从零构建多智能体编排、Red-Blue 对抗降噪、 语义级上下文压缩、跨 Agent 共享记忆四大核心能力,配套 165 次独立实验 + Bootstrap 统计显著性检验的完整评测体系。

    Stale GitHub, qiqihezh 165 ★Updated 6 months ago

    git clone https://github.com/qiqihezh/deepresearch-agent.git
  4. mcp_agent_mail

    Agents & frameworks

    Asynchronous coordination layer for AI coding agents: identities, inboxes, searchable threads, and advisory file leases over FastMCP + Git + SQLite

    Stale GitHub, Dicklesworthstone 2,221 ★Custom licence (see repository)Updated 25 days ago

    git clone https://github.com/Dicklesworthstone/mcp_agent_mail.git
  5. Relax

    Agents & frameworks

    An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

    Indexed GitHub, redai-studio 676 ★Apache-2.0Updated today

    git clone https://github.com/redai-studio/Relax.git
  6. liteflow

    Agents & frameworks

    Lightweight, fast, stable, programmable component-based rule engine — where AI Agents orchestrate just like ordinary components. Uniquely designed DSL: component reuse, sync/async & dynamic orchestration, multi-language scripting, nested rules, hot deployment and smooth refresh. If you can orchestrate LiteFlow, you can orchestrate AI.

    Stale GitHub, dromara 3,883 ★Apache-2.0Updated 56 days ago

    git clone https://github.com/dromara/liteflow.git
  7. Hirepanel

    Agents & frameworks

    Multi-agent resume screening where every score needs a verified quote from the resume. FastAPI, async DAG, n8n, Docker. Human approves every decision.

    Indexed GitHub, punit2911 51 ★MITUpdated 2 days ago

    git clone https://github.com/punit2911/Hirepanel.git
  8. cubeloop

    Agents & frameworks

    CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.

    Stale GitHub, cubeplexai 89 ★MITUpdated 10 days ago

    git clone https://github.com/cubeplexai/cubeloop.git
  9. pi-herdsman

    Agents & frameworks

    Asynchronous Pi subagents and agent fleet orchestration for parallel coding agents with nested delegation, background work, and supervision in herdr.

    Indexed GitHub, boadij 233 ★Apache-2.0Updated today

    git clone https://github.com/boadij/pi-herdsman.git
  10. sagent

    Agents & frameworks

    A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional recursive spawn.

    Indexed GitHub, rekursiv-ai 84 ★Apache-2.0Updated yesterday

    git clone https://github.com/rekursiv-ai/sagent.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.