rewind-memory 0.5.2

Bio-inspired persistent memory for AI agents. 5-layer architecture with FTS5, vector search, knowledge graph, and HybridRAG fusion.

🧠 Rewind Memory

Bio-inspired persistent memory for AI agents.

Rewind gives AI agents structured, persistent memory that works like biological memory — keyword search, knowledge graphs, semantic vectors, score fusion, and intelligent retrieval. Every memory is classified by type (user, feedback, project, reference), weighted by recency, and checked for drift. Runs fully local on SQLite with zero external dependencies.

Architecture

┌─────────────────────────────────────────┐
│            L2 Orchestrator              │
│    (fusion · ranking · deduplication)   │
├─────────┬─────────┬─────────┬──────────┤
│   L0    │   L1    │   L3    │    L4    │
│Sensory  │ System  │  Graph  │  Vector  │
│ Buffer  │  Files  │         │  Search  │
│         │         │         │          │
│ SQLite  │  File   │ SQLite  │sqlite-vec│
│  FTS5   │ system  │  Graph  │ (vec0)   │
└─────────┴─────────┴─────────┴──────────┘

Layers

Layer	Name	Bio Analogy	Backend	Purpose
L0	Sensory Buffer	Sensory cortex	SQLite FTS5	Fast keyword search, BM25 ranking
L1	System Memory	Working memory	File system	Identity, preferences, context — loaded every session
L2	Orchestrator	Prefrontal cortex	In-process	Fuses keyword + graph + vector results
L3	Knowledge Graph	Association cortex	SQLite	Entity relationships, spreading activation, Hebbian learning
L4	Vector Search	Episodic memory	sqlite-vec	Semantic similarity via local embeddings (Ollama)

Quick Start

pip install rewind-memory
rewind doctor                    # Auto-diagnose and fix memory stack
rewind ingest-chats              # Backfill historical OpenClaw conversations
rewind watch                     # Real-time conversation indexing (L0 keyword search)
rewind search "what did we discuss about X"

Full walkthrough: docs/QUICKSTART.md — 5 minutes to first search.

# 1. Install Ollama for vector search (optional but recommended)
curl -fsSL https://ollama.com/install.sh | sh
ollama pull nomic-embed-text  # ~274MB

# 2. Install Rewind
pip install rewind-memory

# 3. Ingest your files
rewind ingest ~/my-project/docs/

# 4. Search
rewind search "what was decided about auth"

Commands

Command	Description
rewind ingest <path>	Ingest files into memory
rewind search <query>	Search memory
rewind health	Health check
rewind doctor	Auto-diagnose and fix issues
rewind watch	Real-time session watcher (NEW in 0.4.7)
rewind ingest-chats	Historical conversation backfill (NEW in 0.4.7)
rewind proxy	Memory-augmented LLM proxy
rewind migrate	Migrate backends (Pro)

Free vs Pro

Feature	Free	Pro
L0 Keyword Search (FTS5)	✅	✅
rewind doctor	✅	✅
rewind watch (L0)	✅	✅
rewind ingest-chats (L0)	✅	✅
L5 Semantic Search (Qdrant)	❌	✅
Multi-channel awareness	❌	✅
Session Extractor	❌	✅
Session Continuity	❌	✅
Neo4j Knowledge Graph	❌	✅
Memory Proxy	✅	✅

Usage

from rewind.client import RewindClient
from rewind.config import default_config

client = RewindClient(default_config("free"))

# Search across all layers
results = client.search("what is Hebbian learning")
for r in results:
    print(f"{r.score:.2f} [{r.layer}] {r.text[:80]}")

# Ingest a document
client.ingest("notes/meeting.md")

# Health check
print(client.health())

CLI

# Search
rewind search "memory consolidation" --limit 10

# Ingest files
rewind ingest ./documents/

# Health check
rewind health

Integrations (Claude Code, Cursor, OpenClaw)

Rewind ships with an MCP server that works with any MCP-compatible tool:

Claude Code — add to ~/.claude/settings.json:

{
  "mcpServers": {
    "rewind": {
      "command": "rewind-mcp"
    }
  }
}

OpenClaw — config setup + optional gateway pre-turn hook:

# Route memory_search through Rewind
rewind-openclaw setup --url http://localhost:8031

# Patch the gateway to auto-inject memory into EVERY inbound message
# (the agent gets memory context before it even starts thinking)
rewind-openclaw patch

Cursor / Windsurf / Cline — add rewind-mcp as an MCP server in settings.

See docs/INTEGRATIONS.md for full setup guides.

Memory Proxy (zero-config, works with any tool)

The proxy auto-injects memory into every LLM call. No MCP needed — just change your API URL:

pip install rewind-memory[proxy]

# Ingest your project first
rewind ingest ./my-project/

# Start the memory proxy
rewind proxy --port 8080

Then point your tool at it:

# Cursor
OPENAI_BASE_URL=http://localhost:8080/v1 cursor .

# Aider
OPENAI_API_BASE=http://localhost:8080/v1 aider

# Any OpenAI-compatible tool
export OPENAI_BASE_URL=http://localhost:8080/v1

The proxy:

• Searches memory on every prompt (keyword + graph + vector fusion)
• Injects relevant context into the system message
• Auto-budgets injection size based on model context limits
• Passes through your API key to the upstream provider
• Supports streaming responses
• Works with OpenAI, Anthropic, NVIDIA, any OpenAI-compatible API

# Point at Anthropic instead of OpenAI
rewind proxy --port 8080 --upstream https://api.anthropic.com/v1

# Point at a local model
rewind proxy --port 8080 --upstream http://localhost:11434/v1

Configuration

# ~/.rewind/config.yaml
tier: free
workspace_path: ~/my-project

embedding:
  provider: ollama
  model: nomic-embed-text
  url: http://localhost:11434

layers:
  l0_sensory: true
  l1_stm: true
  l3_graph: true
  l4_workspace: true

Upgrading

Rewind Core is free and fully functional as a local memory stack. For additional layers (communications, documents, bio lifecycle) and cloud GPU embeddings, see Rewind Pro.

Pro extends the Core package via a plugin — install both and Pro layers activate automatically:

client = RewindClient(default_config("pro"), api_key="rw_live_...")

Feature	Core (Free)	Pro ($9/mo)	MOS (Custom)
Keyword search (FTS5)	✅	✅	✅
System memory	✅	✅	✅
Knowledge graph (SQLite)	✅	✅	✅
Semantic vector search	✅ local Ollama	✅ cloud GPU (A10G)	✅ custom GPU
HybridRAG fusion	✅ 5-layer (L0–L4)	full 7-layer (L0–L6)	full 7-layer
Memory type taxonomy	✅ (user/feedback/project/reference)	✅	✅
Recency weighting	✅ (type-aware decay)	✅	✅
Query-intent matching	✅ (boosts matching types)	✅	✅
Memory drift detection	✅ (flags stale references)	✅	✅
OpenClaw gateway autopatcher	✅ (pre-turn memory injection)	✅	✅
Communications memory (L5)	—	✅	✅
Document store (L6)	—	✅	✅
LLM relevance selection	—	✅ (cheap model side-query)	✅
Cross-encoder reranking	—	✅ (GPU-accelerated)	✅
Memory extraction (post-turn)	—	✅ (auto-extracts durable memories)	✅
Partial compaction	—	✅ (preserves task intent)	✅
Cloud GPU embeddings (NV-Embed-v2)	—	25K/mo included	custom volume rates
Retrieval feedback learning	—	✅	✅
Migration assist (→ Neo4j/Qdrant)	—	✅	✅
Bio lifecycle (decay, pruning)	—	—	✅
Air-gapped deployment	—	—	✅
Dedicated engineer + SLA	—	—	✅

Development

git clone https://github.com/saraidefence/rewind-memory.git
cd rewind-memory
pip install -e ".[dev]"
pytest tests/

Patent

The 7-layer bio-inspired memory architecture is patent pending.

License

Apache License 2.0 — see LICENSE.

---

Built by SARAI Defence. Ukrainian-built. Patent pending.