Squish - AI Memory System for Coding Agents

Connect your sources. Click ingest. Your AI remembers everything.

Squish is an AI memory system for coding agents. Local-first MCP runtime with connectors, knowledge graphs, and multi-tier deployment. Free locally, paid Cloud for sync and teams.

npm i -g squish-memory && squish install --all

Squish Demo

Core Concepts

Concept	What It Is
Recall	Durable memory — decisions, preferences, constraints
Sessions	Evidence from past agent runs
Pinned	Stable facts that do not decay
Beliefs	Passive model of user/project
Strategies	Active operating rules
Decay	Stale weak traces fade automatically
Graph	Reinforced relationships from usage

The Problem: Agents Forget Everything

Every AI coding agent starts from zero when a new session begins. The architecture decision from last week, the config you spent an hour debugging, the preference you mentioned yesterday — gone.

Built-in memory files like CLAUDE.md and .cursorrules help, but they have hard limits. They cap out around 200 lines, require manual curation, and do not work across agents. You end up copy-pasting the same context into every tool.

Squish gives you persistent memory for coding agents that scales without limits. No manual maintenance. No token waste. No agent lock-in.

Three Layers of Memory

Layer	What It Does	Command
Recall	Durable memory — decisions, preferences, constraints that persist across sessions	`squish recall`
Sessions	Searchable history — past agent runs you can inspect for evidence and context	`squish sessions search`
Remember	Write to long-term memory — store new facts, decisions, observations	`squish remember`

Token Cost Comparison

Method	Token Usage	Cost per Session	Cross-Agent	Auto-Capture
Paste full context	~2,000 tokens	$0.06 - $0.12	No	No
LLM-summarized context	~500 tokens	$0.02 - $0.05	No	No
CLAUDE.md / .cursorrules	~200 lines max	Free	No	No
Squish (local)	~50-200 tokens	$0.00	Yes	Yes
Squish (Cloud)	~50-200 tokens	$0.00	Yes	Yes

Squish retrieves only the relevant memories for the current task. The average context injection is 50-200 tokens — a fraction of what you would paste manually.

Quick Start

Step 1: Install

npm install -g squish-memory && squish install --all

This installs the Squish CLI, MCP server, and plugin hooks for all detected agents.

Step 2: Work

Start your coding agent as usual. Squish runs in the background, auto-capturing decisions, constraints, preferences, and context.

squish remember "We chose PostgreSQL for Squish Cloud team mode" --type decision
squish recall "project decisions"

Step 3: Search Past Sessions

After a few sessions, search your agent history:

squish sessions search "postgres migration"
squish sessions related --repo-path .

Step 4: Restart

Close your session and open a new one. Your agent picks up where you left off — all context is restored automatically.

squish context    # See what your agent remembers
squish stats      # Check memory health

Works locally free. Paid Squish Cloud is available at squishplugin.dev for sync, dashboard, and team features.

Works with Every Agent

Squish works with any AI coding agent that supports MCP (Model Context Protocol) or HTTP connections. One memory server, shared across all of them.

Agent	Integration Method	Notes
Claude Code	MCP server + plugin	Auto-captures via hooks
Codex CLI	MCP server	OpenAI's CLI agent
GitHub Copilot CLI	MCP server	VS Code integration
Cursor	MCP server	Editor + agent
Gemini CLI	MCP server	Google's CLI agent
OpenCode	MCP server + hooks	Auto-capture + MCP tools
Cline	MCP server	VS Code extension
Goose	MCP server	Block's agent
Kilo Code	MCP server	VS Code extension
Windsurf	MCP server	Codeium's editor
Roo Code	MCP server	VS Code extension
Claude Desktop	MCP server	Desktop app
Aider	MCP server	Terminal pair programmer
ChatGPT	MCP server (via Squish Cloud)	Cloud sync required
VS Code (Copilot)	MCP server	Via MCP extension

Works with any agent that speaks MCP or HTTP. One server, memories shared across all of them.

MCP Server Configuration

Add Squish to any MCP-compatible client:

{
  "mcpServers": {
    "squish": {
      "command": "squish-mcp",
      "args": ["--http", "--port", "8767"],
      "env": {
        "SQUISH_DB_PATH": "./squish-data"
      }
    }
  }
}

For cloud-connected agents:

{
  "mcpServers": {
    "squish-cloud": {
      "type": "url",
      "url": "https://api.squishplugin.dev/mcp",
      "headers": {
        "Authorization": "Bearer <your-token>"
      }
    }
  }
}

Why Squish

Most memory tools need a second LLM for embeddings and retrieval. That means extra API costs, latency, and infrastructure you have to manage.

Squish uses local embeddings by default. Zero LLM dependency. 1-5ms latency. $0 runtime cost in local mode.

Bring your own LLM if you want — Squish supports external embeddings and reasoning, but nothing requires it.

Comparison

Feature	Squish	Built-in (CLAUDE.md)	agentmemory	mem0
Auto-capture	Yes (hooks)	Manual	Yes (12 hooks)	Manual API
Local embeddings	Yes (default)	N/A	Yes	No (cloud)
External DB required	No (SQLite)	No	Yes (iii-engine)	Yes (Qdrant)
MCP tools	18	0	53	9
Knowledge graph	Yes	No	Yes	No
Cross-agent sync	Yes (Cloud)	No	No	API-based
Price	Free local / $9/mo cloud	Free	Free	$249/mo Pro
Setup time	30 seconds	5 minutes	15 minutes	30 minutes
Data ownership	Full (local SQLite)	Git repo	External DB	Cloud vendor

Features

Memory Intelligence

Auto-captures decisions, constraints, and preferences as you work
Restores relevant context when an agent restarts
Handles contradictions and temporal facts with expiration
Graph-boosted retrieval connects related memories across sessions
Contradiction detection flags conflicting information
Temporal reasoning tracks when facts were true vs. now
Confidence scoring adjusts memory relevance over time
Decay system automatically ages low-value memories

Session Search

Search previous Claude Code, Codex, and OpenCode sessions
Find related sessions by project path or file overlap
Inspect past decisions, errors, and commands as evidence
Separate from long-term memory — raw session history, not distilled facts

Interfaces

CLI: squish remember, recall, inspect, context, stats, search, sessions
MCP Server: 18 tools for any MCP client — recall, health, graph, recency, maintenance
Web UI: Local dashboard at localhost:37777 for visualizing memories
Cloud Dashboard: Paid analytics and management at squishplugin.dev

Storage

SQLite (local, default) or Squish Cloud team workspaces
Hybrid retrieval: keyword + semantic similarity with RRF fusion
AES-256-GCM encryption for sensitive memories
Places routing: organize memories by project, feature, or context
Full-text search with BM25 ranking
Vector search with TF-IDF embeddings (768-dimensional)

Memory Pipeline

Squish uses a 4-stage pipeline to process memories:

Capture — Filters noisy tool output, keeps new memories private-first, and suggests what should be promoted into project/team/company scopes
Filter — Deduplicates, resolves contradictions, scores importance
Store — Persists to SQLite/PostgreSQL with graph relationships and embeddings
Retrieve — Hybrid search combines keyword, semantic, recency, and importance scoring

Architecture

Three-Layer Memory Model

Storage Layer

SQLite (default)	Squish Cloud Team
memories	memories
associations	associations
embeddings	embeddings
graph_edges	graph_edges
places	places
sessions	sessions
AES-256-GCM encryption	AES-256-GCM encryption

Connectors

Squish connects to your existing tools and ingests context automatically:

Connector	What It Ingests
Google Drive	Documents, sheets, slides, and files
GitHub	Issues, PRs, discussions, code context, and repo metadata
Slack	Messages, threads, channel context, and decisions
Notion	Pages, databases, docs, and wikis

Connectors are available on Cloud tiers. Install with:

squish connect google-drive
squish connect github
squish connect slack
squish connect notion

Ingestion Pipeline

Squish uses a 4-stage pipeline to process content from your connectors:

Chunk -- Splits documents into meaningful segments
Embed -- Generates TF-IDF or external embeddings (768-dimensional vectors)
Store -- Persists to SQLite/PostgreSQL with graph relationships
Extract -- Builds knowledge graph with entity resolution and relationship mapping

Optional LLM-powered features (bring your own key):

Entity extraction and relationship mapping
Automatic memory organization and tagging
Summarization and consolidation

Squish Cloud

Persistent memory across ChatGPT, Claude Desktop, Claude Code, and local agents. One account, synchronized everywhere.

Squish Cloud Architecture

Cloud features: OAuth 2.1 + PKCE login, cross-platform sync, team workspaces, admin dashboard, priority support.

Pricing

Tier	Price	Features
Local	Free forever	SQLite, 15+ MCP tools, offline, knowledge graph, decay scoring
Cloud Solo	$9/mo	Everything in Local + cloud sync, 1 connector, 10K requests/mo
Cloud Pro	$29/mo	Cross-tool sync, 3 connectors, 50K requests/mo, shared workspaces
Cloud Team	$99/mo	Unlimited seats, all connectors, 200K requests/mo, RBAC, audit logs

Installation Guides

Claude Code — MCP server + plugin hooks for auto-capture
OpenCode — MCP server + hooks for OpenCode agent
OpenClaw — MCP server setup for OpenClaw

Quick install for all detected agents:

npm install -g squish-memory && squish install --all

Squish auto-detects which agents you have installed and configures hooks for each one.

Benchmarks

Squish is tested against real-world memory retrieval tasks and synthetic benchmarks.

Metric	Result	Notes
Core Tests	9/9 passed (100%)	All memory operations
LoCoMo Memory	65%	100 REAL questions from locomo10.json
Throughput	39 ops/sec	With local embeddings
Total Time	230ms	For 9 core tests
Package Size	283 KB	Lightweight footprint
Latency (embed)	6.6ms	Local TF-IDF embeddings
Latency (search)	6.1ms	Hybrid retrieval

Full benchmark details: docs/BENCHMARK.md

Documentation

Document	Description
CLI Reference	All CLI commands and options
MCP Server	18 MCP tools and configuration
Architecture	System design and data flow
Decay System	How memories age and lose relevance
Scoring	Importance and relevance scoring
Environment Config	Environment variables and settings
Plugin Architecture	Hook system and agent integration
Quick Start	Getting started guide
Agent Comparison	Squish vs other memory tools
Contributing	How to contribute
Release Notes	Changelog and version history

FAQ

What is Squish?

Squish is a local-first memory runtime for AI coding agents. It gives your agents stable orientation, durable memory, and searchable session history across runs. Think of it as a brain that persists between sessions — your agents remember decisions, constraints, preferences, and context without you having to re-explain everything. In v1.6.0, Squish also searches past agent sessions as evidence, so agents can inspect prior work instead of starting from zero.

Does Squish require an API key?

No. Squish works locally by default with zero API keys. It uses local embeddings (TF-IDF) and SQLite storage. You can optionally configure an external LLM for enhanced reasoning, but it's not required. An API key is only needed if you want to use the paid Squish Cloud for cross-device sync.

How does Squish compare to mem0 or agentmemory?

Squish is the only option that works locally with zero external dependencies. mem0 requires Qdrant (a vector database) and cloud API calls. agentmemory requires iii-engine. Squish uses SQLite and local embeddings by default. See the full comparison in the Why Squish section above.

Can I use Squish with multiple AI agents?

Yes. Squish works with any MCP-compatible agent. One memory server is shared across Claude Code, Cursor, Codex, Copilot, Gemini CLI, and any other agent that supports MCP. Memories are available to all connected agents.

Is my data private with Squish?

Yes. In local mode, all data stays on your machine in an encrypted SQLite database. Nothing is sent to any cloud service. AES-256-GCM encryption protects sensitive memories. In cloud mode, data is encrypted in transit and at rest.

What databases does Squish support?

Squish supports SQLite (default, local) and Squish Cloud team workspaces backed by PostgreSQL. SQLite requires zero configuration. Team workspaces are only available on Squish Cloud and are used for shared memory across multiple users.

What is the difference between recall and sessions?

squish recall searches your long-term memory — distilled facts, decisions, and preferences that Squish has captured and organized. squish sessions search searches raw past agent runs — the actual messages, commands, and file changes from previous Claude Code, Codex, or OpenCode sessions. Recall gives you what the system decided to remember. Sessions give you the evidence.

Contributing

See docs/CONTRIBUTING.md for guidelines on how to contribute to Squish.

License

MIT -- see LICENSE for details.

Website · Cloud Dashboard · Documentation · GitHub · npm