by metaevo-ai · Agent Tool · ★ 104
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
[ICML 2026] Meta Context Engineering via Agentic Skill Evolution Superseding Static Harnesses with Learnable Skills for Context Optimization This repository accompanies the paper Meta Context Engineering via Agentic Skill Evolution. Meta Context Engineering (MCE) is a bi-level agentic framework that co-evolves context engineering skills and context artifacts, replacing rigid CE heuristics with learnable skills that automatically discover optimal context representations and optimization procedures. Key Results MCE achieves consistent improvements across five diverse domains (finance, chemistry, medicine, law, AI safety): Efficiency gains: 13.6× faster training than ACE 4.8× fewer rol
| Stars | 104 |
| Forks | 10 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 73.3930551953919/100 |
| Open Issues | 1 |
| Last Updated | 2026-05-04 |
| Created | 2026-01-29 |
| Platforms | claude-code, python |
| Est. Tokens | ~790k |
These tools work well together with meta-context-engineering for enhanced workflows:
Looking for a meta-context-engineering alternative? If you're comparing meta-context-engineering with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.
🧠 Context Engineering Research - Not just another agent collection, but using research and context engineerin
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
AI agent tooling for data engineering workflows.
A VSCode extension that lets you find and install Agent Skills and MCP Apps to use with GitHub Copilot, Claude
Copy AI conversations as clean Markdown Context Bundles — one click from ChatGPT, Claude, Gemini, DeepSeek, Gr
Explore other popular agent tool tools:
meta-context-engineering is [ICML 2026] Meta Context Engineering via Agentic Skill Evolution. It is categorized as a Agent Tool with 104 GitHub stars.
meta-context-engineering is primarily written in Python. It covers topics such as agent-skills, agents, claude.
You can find installation instructions and usage details in the meta-context-engineering GitHub repository at github.com/metaevo-ai/meta-context-engineering. The project has 104 stars and 10 forks, indicating an active community.
meta-context-engineering is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to meta-context-engineering on Agent Skills Hub include skillport, claude-code-sub-agent-collective, tutor-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.