What is the altk-evolve MCP server?

AgentToolkit/altk-evolve — Self improving agents through iterations AgentRank score: 67.4/100.

Is the altk-evolve MCP server actively maintained?

The altk-evolve MCP server was last committed 29d ago and has 9 contributors. Issue health: 33% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

altk-evolve MCP Server

Name: AgentToolkit/altk-evolve
Rating: 3.7 (1 reviews)
Author: AgentToolkit

AgentToolkit/altk-evolve

Score: 67.4 Rank #4584 Monitoring

[![AgentRank](https://agentrank-ai.com/api/v1/badge/AgentToolkit--altk-evolve)](https://agentrank-ai.com/tool/AgentToolkit--altk-evolve/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of AgentToolkit/altk-evolve? Claim this listing →

Self improving agents through iterations

Add AgentRank to Claude Code Discover and compare tools like AgentToolkit/altk-evolve — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

AgentToolkit/altk-evolve is a Python tool licensed under Apache-2.0. Self improving agents through iterations Topics: agent-learning, claude-code-plugin, mcp, agent-memory, ai-agents, episodic-memory, model-context-protocol, observability, claude-code-plugins, claude-code, codex, llm, trajectory, vector-database, agentic-workflows, memory, self-evolution, self-learning-ai, context-management.

Ranked #4584 out of 24846 indexed tools.

Ecosystem

Python Apache-2.0 519 pypi/wk

agent-learningclaude-code-pluginmcpagent-memoryai-agentsepisodic-memorymodel-context-protocolobservabilityclaude-code-pluginsclaude-codecodexllmtrajectoryvector-databaseagentic-workflowsmemoryself-evolutionself-learning-aicontext-management

Score Breakdown

Stars 15% 123

123 stars → growing community

Freshness 25% 29d ago

Last commit 29d ago → recently updated

Issue Health 25% 33%

47/144 issues closed → many open issues

Contributors 10% 9

9 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads 13% 519/wk

519 weekly installs → early adoption

Forks 18

Description Brief

License Apache-2.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Issue Health high impact

You have 97 open vs 47 closed issues — triaging stale issues improves health

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/AgentToolkit--altk-evolve)](https://agentrank-ai.com/tool/AgentToolkit--altk-evolve/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/AgentToolkit--altk-evolve/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/AgentToolkit--altk-evolve" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="AgentToolkit/altk-evolve"></script>

Details

Stars: 123
Forks: 18
Open Issues: 97
Closed Issues: 47
Contributors: 9
Dependents: —
Language: Python
License: Apache-2.0
Last Commit: 29d ago

Matched Queries

topic:mcptopic:model-context-protocol

From the README

<div align="center">

# Evolve: On‑the‑job learning for AI agents

</div>

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 improve over time by learning from their trajectories. The Lite version is designed to effortlessly slot into existing agent assistants like Claude Code and Codex. It uses a combination of an MCP server for tool integration, vector storage for memory, and LLM-based conflict resolution to refine its knowledge base.

On the AppWorld benchmark, Evolve improved agent reliability by +8.9 points overall, with a 74% relative increase on hard multi-step tasks. Evolve is a system designed to help agents improve over time by learning from their trajectories. It uses a combination of an MCP server for tool integration, vector storage for memory, and LLM-based conflict resolution to refine

Read full README on GitHub →