Recluse

HyperMnesia — Data skill for Claude Code

Data community

Self-hosted long-term memory for AI coding agents: Postgres+pgvector doc-RAG (component/constraint map + hybrid RRF + cross-encoder rerank) and bi-temporal personal memory.

How to install HyperMnesia

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Recluse/HyperMnesia and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What HyperMnesia does

Self-hosted long-term memory for AI coding agents: Postgres+pgvector doc-RAG (component/constraint map + hybrid RRF + cross-encoder rerank) and bi-temporal personal memory. MCP-native, local-model friendly.

Alternatives in Data

Private GPT — Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more 57.5k ★
OpenViking — Self-evolving Context Database for AI Agents 33.3k ★
Sprite Gen — Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame 763 ★

README

HyperMnesia

*The opposite of amnesia* (Greek *hypermnesia* -- abnormally complete recall). Self-hosted long-term memory for AI coding agents -- a Postgres-backed store that gives an agent (Claude Code, or any MCP client) two things:

Architectural memory (doc-RAG + Tier 0/1) -- your repos' docs made searchable, plus a deterministic component -> constraint model so the agent knows the rules that apply to a file before it edits, without a search.
Personal memory -- durable facts/preferences/decisions distilled from work sessions and injected back automatically, so the agent stops re-learning the same things every session.

One store (Postgres + [pgvector](https://github.com/pgvector/pgvector)), local-model friendly (embeddings via [Ollama](https://ollama.com) or [TEI](https://github.com/huggingface/text-embeddings-inference)), MCP-native, no cloud dependency. Runs on a laptop, one server, or Kubernetes.

Not a vector-DB wrapper. The value is the **delivery**: deterministic constraint injection (Tier 1) and hook-driven personal-memory capture/recall -- "storage is solved, injection isn't."

How it works

                 +---------------- retrieval ----------------+
   query --> Tier 0: pinned project map + global invariants   |
             Tier 1: path -> component -> must/should constraints (+1-hop graph)   <- deterministic
             Tier 2: hybrid RRF search (pgvector cosine + Postgres FTS) + rerank  <- fuzzy
                 +-------------------------------------------+

Tier 2 search fuses dense (bge-m3 embeddings, HNSW) and lexical (composite tsvector, works for code identifiers and non-English) via Reciprocal Rank Fusion, then an optional cross-encoder reranker (bge-reranker-v2-m3) reorders the top candidates (measured +0.16 recall@1 on our eval set).
Personal memory is bi-temporal (event time vs ingestion time), **supersede-not-overwr