Acontext and Agent-Skills

These tools are ecosystem siblings, with Acontext providing a memory layer for agent skills that could be utilized to store and manage the structured expertise offered by Agent-Skills for AI coding assistants.

Acontext
70
Verified
Agent-Skills
50
Established
Maintenance 25/25
Adoption 10/25
Maturity 15/25
Community 20/25
Maintenance 13/25
Adoption 10/25
Maturity 11/25
Community 16/25
Stars: 3,154
Forks: 296
Downloads:
Commits (30d): 174
Language: TypeScript
License: Apache-2.0
Stars: 400
Forks: 36
Downloads:
Commits (30d): 0
Language:
License: CC-BY-4.0
No Package No Dependents
No Package No Dependents

About Acontext

memodb-io/Acontext

Agent Skills as a Memory Layer

Implements automatic skill extraction and progressive-disclosure retrieval without embeddings—using a "Skill Agent" to distill conversation traces into editable Markdown files that agents can fetch via tool calls. Supports Python and TypeScript SDKs, integrates with LangGraph and Claude, and persists skills as version-controllable files with optional self-hosting via Docker.

About Agent-Skills

MicrosoftDocs/Agent-Skills

Curated Agent Skills for Microsoft & Azure – giving AI coding assistants structured, real-time expertise from Microsoft Learn docs.

Implements the **Agent Skills open standard** with filesystem-based skill discovery across eight AI coding assistants (Claude Code, Gemini CLI, GitHub Copilot, Cursor, etc.), organizing Azure expertise into progressive disclosure levels—YAML metadata for discovery, markdown instructions on trigger, and supplementary resources on demand. Pre-compiles Microsoft Learn documentation into structured, executable skills that encode API patterns, configuration procedures, best practices, and troubleshooting decision trees rather than relying on retrieval-augmented generation to interpret raw text each time.

Scores updated daily from GitHub, PyPI, and npm data. How scores work