Jasper Recall

# Jasper Recall v0.2.3

Local RAG (Retrieval-Augmented Generation) system for AI agent memory. Gives your agent the ability to remember and search past conversations.

**New in v0.2.2:** Shared ChromaDB Collections — separate collections for private, shared, and learnings content. Better isolation for multi-agent setups.

**New in v0.2.1:** Recall Server — HTTP API for Docker-isolated agents that can't run CLI directly.

**New in v0.2.0:** Shared Agent Memory — bidirectional learning between main and sandboxed agents with privacy controls.

## When to Use

- **Memory recall**: Search past sessions for context before answering
- **Continuous learning**: Index daily notes and decisions for future reference
- **Session continuity**: Remember what happened across restarts
- **Knowledge base**: Build searchable documentation from your agent's experience

## Quick Start

### Setup

One command installs everything:

```bash
npx jasper-recall setup
```

This creates:
- Python venv at `~/.openclaw/rag-env`
- ChromaDB database at `~/.openclaw/chroma-db`
- CLI scripts in `~/.local/bin/`
- OpenClaw plugin config in `openclaw.json`

### Why Python?

The core search and embedding functionality uses Python libraries:

- **ChromaDB** — Vector database for semantic search
- **sentence-transformers** — Local embedding models (no API needed)

These are the gold standard for local RAG. There are no good Node.js equivalents that work fully offline.

### Why a Separate Venv?

The venv at `~/.openclaw/rag-env` provides:

| Benefit | Why It Matters |
|---------|----------------|
| **Isolation** | Won't conflict with your other Python projects |
| **No sudo** | Installs to your home directory, no root needed |
| **Clean uninstall** | Delete the folder and it's gone |
| **Reproducibility** | Same versions everywhere |

The dependencies are heavy (~200MB total with the embedding model), but this is a one-time download that runs entirely locally.

### Basic Usage

**Search your memory:**
```ba...

# Jasper Recall 🦊

Local RAG (Retrieval-Augmented Generation) system for AI agent memory. Gives your agent the ability to remember and search past conversations using ChromaDB and sentence-transformers.

## Features

- **Semantic search** over session logs and memory files
- **Local embeddings** — no API keys needed
- **Incremental indexing** — only processes changed files
- **Session digests** — automatically extracts key info from chat logs
- **OpenClaw integration** — works seamlessly with OpenClaw agents

### New in v0.2.0: Shared Agent Memory

- **Memory tagging** — Mark entries `[public]` or `[private]` to control visibility
- **Privacy filtering** — `--public-only` flag for sandboxed agents
- **Shared memory sync** — Bidirectional learning between main and sandboxed agents
- **Privacy checker** — Scan content for sensitive data before sharing

### New in v0.3.0: Multi-Agent Mesh (JR-19)

- **Multi-agent memory sharing** — N agents can share memory, not just 2
- **Agent-specific collections** — Each agent gets private memory (`agent_sonnet`, `agent_qwen`, etc.)
- **Mesh queries** — Query across multiple agents: `recall-mesh "query" --mesh sonnet,qwen,opus`
- **Backward compatible** — Legacy collections still work

### New in v0.2.1: Recall Server

- **HTTP API server** — `npx jasper-recall serve` for Docker-isolated agents
- **Public-only by default** — Secure API access for untrusted callers
- **CORS enabled** — Works from browsers and agent containers

## Quick Start

```bash
# One-command setup
npx jasper-recall setup

# Search your memory
recall "what did we decide about the API"

# Index your files
index-digests

# Process new session logs
digest-sessions
```

### Multi-Agent Mesh (v0.3.0+)

```bash
# Index memory for specific agents
index-digests-mesh --agent sonnet
index-digests-mesh --agent qwen

# Query as specific agent
recall-mesh "query" --agent sonnet

# Query across multiple agents (mesh mode)
recall-mesh "query" --mesh sonnet,qwen,opus
```

See...