Acontext and agent-skills

These tools are complements: `memodb-io/Acontext` provides the foundational memory layer for agent skills, while `supabase/agent-skills` offers a collection of pre-built agent skills specifically designed to integrate with Supabase, potentially utilizing a memory layer like Acontext.

Acontext
70
Verified
agent-skills
51
Established
Maintenance 25/25
Adoption 10/25
Maturity 15/25
Community 20/25
Maintenance 13/25
Adoption 10/25
Maturity 11/25
Community 17/25
Stars: 3,154
Forks: 296
Downloads:
Commits (30d): 174
Language: TypeScript
License: Apache-2.0
Stars: 1,584
Forks: 94
Downloads:
Commits (30d): 1
Language: TypeScript
License: MIT
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

supabase/agent-skills

Agent Skills to help developers using AI agents with Supabase

Provides curated Postgres optimization guidelines and best practices as discoverable skills for AI coding assistants (Claude Code, Cursor, GitHub Copilot), following the open Agent Skills standard format. Skills are automatically injected into agent contexts when relevant tasks are detected, enabling agents to reference 8 categories of performance guidance—from query optimization to RLS configuration—without explicit prompting. Installable via npm or Claude's plugin marketplace for seamless integration into existing agent workflows.

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