DeepRecall v2 — OpenClaw Skill

Pure-Python recursive memory for persistent AI agents. Implements the Anamnesis Architecture: "The soul stays small, the mind scales forever."

Description

DeepRecall gives AI agents infinite memory by recursively querying their own memory files through a manager→workers→synthesis RLM loop — entirely in Python. No Deno runtime, no fast-rlm subprocess, no vector database. Just markdown files and HTTP calls to any OpenAI-compatible LLM endpoint.

When the agent needs to recall something, DeepRecall:

1. Scans the workspace for memory files (scoped by category)
2. Indexes file metadata — headers, topics, dates, people
3. Manager selects the most relevant files from the index
4. Workers (parallel) extract exact verbatim quotes from each file
5. Synthesis combines quotes into a cited, grounded answer