altk-evolve — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by AgentToolkit · MCP Server · ★ 112

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is altk-evolve safe to install? View the security audit →

About altk-evolve

Evolve: On‑the‑job learning for AI agents Blog posts: IBM announcement | Hugging Face blog 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, wit

agent-learningagent-memoryagentic-workflowsai-agentsclaude-codeclaude-code-pluginclaude-code-pluginscodexcontext-managementepisodic-memory

Quick Facts

Stars112
Forks15
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score70.6691355929454/100
Open Issues71
Last Updated2026-09-18
Created2025-12-12
Platformsclaude-code, codex, mcp, python
Est. Tokens~15k

altk-evolve alternative? Top 6 similar tools

Looking for a altk-evolve alternative? If you're comparing altk-evolve with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • engrim by timgordontg · ⭐ 280

    The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antig

  • Ori-Mnemos by aayoawoyemi · ⭐ 324

    Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

  • iai-mcp by CodeAbra · ⭐ 119

    The best-benchmarked open-source memory system for AI coding assistants

  • claude-emporium by Vvkmnn · ⭐ 84

    🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace

  • Commonly-used-high-value-skills by seaworld008 · ⭐ 70

    High-value AI skills repository for Codex, Claude Code, OpenClaw, agents, prompts, and automation workflows.

  • openexp by anthroos · ⭐ 59

    Outsource your understanding. Capture every human-AI decision as a step in a trajectory; grade trajectories re

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is altk-evolve?

altk-evolve is Self improving agents through iterations. It is categorized as a MCP Server with 112 GitHub stars.

What programming language is altk-evolve written in?

altk-evolve is primarily written in Python. It covers topics such as agent-learning, agent-memory, agentic-workflows.

How do I install or use altk-evolve?

You can find installation instructions and usage details in the altk-evolve GitHub repository at github.com/AgentToolkit/altk-evolve. The project has 112 stars and 15 forks, indicating an active community.

What license does altk-evolve use?

altk-evolve is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to altk-evolve?

The top alternatives to altk-evolve on Agent Skills Hub include engrim, Ori-Mnemos, iai-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools