InnerVault

evolving-agents

Stale GitHub, EvolvingAgentsLabs

A director agent that learns how your team works: it plans by walking your CLAUDE.md and memory as linked statements, delegates to Claude Code or local models, and keeps each lesson as a gated, versioned patch. Measured: 0.929 vs 0.589.

Open the source (opens github.com) https://github.com/evolvingagentslabs/evolving-agents

What it is

Agents & frameworks from EvolvingAgentsLabs.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

How to get it

Get the code

git clone https://github.com/EvolvingAgentsLabs/evolving-agents.git

Standard git access to a public repository

Setup steps: not provided by the source. Follow the instructions on the source.

Related

  1. GenericAgent

    Agents & frameworks

    Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

    Stale GitHub, lsdefine 14.4k ★MITUpdated 10 days ago

    git clone https://github.com/lsdefine/GenericAgent.git
  2. Proteus

    Agents & frameworks

    Self-evolution for any agent harness. Plug in. Evolve. Measure.

    Indexed GitHub, proteus-evolve 112 ★MITUpdated 2 days ago

    git clone https://github.com/proteus-evolve/Proteus.git
  3. 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
  4. KADATH

    Agents & frameworks

    Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimization of a goal.

    Stale GitHub, i3T4AN 253 ★Apache-2.0Updated 23 days ago

    git clone https://github.com/i3T4AN/KADATH.git
  5. Yunjue-Agent

    Agents & frameworks

    Yunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks

    Stale GitHub, YunjueTech 536 ★Apache-2.0Updated 8 months ago

    git clone https://github.com/YunjueTech/Yunjue-Agent.git
  6. Sage

    Agents & frameworks

    An RSI Agent Harness for running, evaluating, and evolving agents—with tools, skills, MCP, stateful execution, and multi-agent workflows.

    Indexed GitHub, ZHangZHengEric 1,215 ★MITUpdated yesterday

    git clone https://github.com/ZHangZHengEric/Sage.git