Pinned Loading

1. agent-memory agent-memory Public

   Verifiable memory for LLM agents — every recalled claim is HMAC-signed back to its originating trajectory span.

   Python 8 1

2. obsidian_mcp obsidian_mcp Public

   MCP server + 7 Claude skills for Obsidian vaults — read, search, write, and link notes from Claude / Cursor / ChatGPT. Filesystem-direct, local-first, round-trip safe.

   Python 8

3. awesome-why-llms-work awesome-why-llms-work Public

   A falsifiable-hypothesis atlas of why LLMs work: five competing research programmes, 41 tracked claims with epistemic status (🟢🟡🔴⚪) and named falsifiers.

   Python 6

4. capture-engine capture-engine Public

   Capture any web page as vector PDF, standalone HTML, or high-DPR raster, crisp at any zoom, local-only, MV3.

   TypeScript 6

5. llm-interview-prep llm-interview-prep Public

   JavaScript 6

6. mcp-postgres mcp-postgres Public

   A Postgres MCP server for agents — layered safety (role grant + pglast AST guard + per-tx envelope + audit log), schema introspection, EXPLAIN analysis, pgvector. PG 13–17.

   Python 7