Skip to main content
v15.0.0Persistent memory for AI coding agents

Build software from specifications, not prompts.

Attune gives AI coding agents persistent project memory and a reliability layer that keeps changes grounded in your code, aligned with your requirements, and verified before they ship.

Or install it as a Claude Code plugin — no Python required.

Free and open source · Apache 2.025,000+ tests | 85% coverage

Your AI is smart. Your project has amnesia.

A coding agent spends hours learning your architecture, your constraints, your conventions, the decisions behind the code, and the approaches that already failed. Then the session ends — and most of that knowledge is gone. The next session, the next tool, the next model: each one starts rediscovering your project from zero.

Attune makes that knowledge persistent.

How it works

One reliability loop

Every change moves through the same five stages — from a requirement you can point at to an implementation you can trust.

  1. 01

    Specify

    Socratic spec engine: requirements, design, and tasks with an approval gate.

  2. 02

    Ground

    RAG retrieval cites your code so the agent doesn't invent APIs.

  3. 03

    Build

    21 workflows: review, tests, bug prediction, refactor.

  4. 04

    Remember

    Cross-session memory and a lessons corpus surface what worked before.

  5. 05

    Verify

    Fact-check generated content: imports, flags, links, counts — all real.

Project memory

Your agent stops starting from zero.

Findings from each session are stashed and recalled in the next — automatically, or on demand with /recall. What persists:

  • Architectural decisions

    why the code is shaped the way it is

  • Coding conventions

    the patterns your reviewers actually enforce

  • Discovered constraints

    the limits that are not written down anywhere

  • Lessons from failed approaches

    so the same dead end is not explored twice

  • Implementation details

    the seams, gotchas, and load-bearing quirks

  • Project-specific knowledge

    domain terms, priorities, and context

Local-first by default — memory lives on your machine, no cloud required. An optional Redis tier adds semantic recall with local Ollama embeddings.

Multi-agent

One project brain. Multiple agents.

Attune is the persistent layer beneath your coding agents, not a feature of one of them. Claude Code, Codex, and Antigravity work against the same project memory, specs, lessons, and repository state — handing off work with git-verified packets and giving each other second opinions on real diffs.

Claude Code
Codex
Antigravity
ATTUNE PROJECT BRAIN
Memory · Specs · Lessons · Grounding · Verification
Your repository
Cross-model review and deliberation are advisory — you decide what gets adopted.

Measured, not promised.

25,000+
automated tests
85%
coverage floor, CI-enforced
0.97
mean RAG faithfulness, CI-gated
100%
open source · Apache 2.0

Inspect everything.

Attune is open source under the Apache License 2.0. Every workflow, every memory operation, every verification step is code you can read, modify, evaluate, and use — commercially included. No black box between your agent and your repository.

View the source on GitHub

Get started

In Claude Code

Works standalone
$ claude plugin marketplace add Smart-AI-Memory/attune-ai
$ claude plugin install attune-ai@attune-ai

No Python environment required. Runs on your existing Claude subscription — then type /spec or /coach to start.

Python package

Adds CLI + MCP
$ pip install attune-ai

Unlocks the CLI, the MCP server, and multi-agent workflows. With ANTHROPIC_API_KEY set, large modules fall back to the Anthropic API — API usage bills API credits, separate from a Claude subscription.

Project memory, retrieval, and the help system are local-first — no API key, no cloud required.

Full installation guide →

Your coding agent shouldn't forget yesterday.

Give it a persistent project memory.