altk-evolve

by AgentToolkit · Python · ★ 79

Self improving agents through iterations

#agent-learning#agent-memory#agentic-workflows#ai-agents#claude-code#claude-code-plugin#claude-code-plugins#codex#context-management#episodic-memory#llm#mcp#memory#model-context-protocol#observability#self-evolution#self-learning-ai#trajectory#vector-database

Install

pip install git+https://github.com/AgentToolkit/altk-evolve.git

Claude Desktop config

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "altk-evolve": {
      "command": "uvx",
      "args": [
        "git+https://github.com/AgentToolkit/altk-evolve.git"
      ]
    }
  }
}

From the README

[](https://www.python.org/) [](https://agenttoolkit.github.io/altk-evolve) [](https://arxiv.org/pdf/2603.10600) [](https://www.apache.org/licenses/LICENSE-2.0) **Blog posts:** [IBM announcement](https://www.ibm.com/new/announcements/altk-evolve-on-the-job-learning-for-ai-agents) | [Hugging Face blog](https://huggingface.co/blog/ibm-research/altk-evolve) Coding agents repeat the same mistakes because they start fresh every session. Evolve gives agents memory — they learn from what worked and what didn't, so each session is better than the last. Evolve is a system designed to help agents imp…

Read full README on GitHub →