Stash MCP Server

<p align="center"> <a href="https://joinstash.ai"><img src="docs/assets/logo.svg" alt="Stash" width="320" /></a> </p> <h3 align="center">Help your agents learn from experience.</h3> <p align="center"> Agents generate valuable experience every time they work: successful approaches, <br> failed attempts, and human corrections. Stash captures that history and makes <br> its lessons available to future runs. </p> <p align="center"> <a href="https://github.com/Fergana-Labs/stash/actions/workflows/test.yml"><img src="https://github.com/Fergana-Labs/stash/actions/workflows/test.yml/badge.svg?branch=main" alt="CI" /></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT" /></a> <a href="https://joinstash.ai"><img src="https://img.shields.io/badge/Website-joinstash.ai-F97316" alt="Website" /></a> <a href="https://discord.gg/PVFdcQx2u3"><img src="https://img.shields.io/badge/Discord-Join%20us-5865F2?logo=discord&logoColor=white" alt="Discord" /></a> </p>

This repository provides the open-source foundation: trace collection, persistent knowledge, and reusable skills, accessible through a Python SDK, REST API, MCP, and CLI. It works alongside your existing agents and models.

flowchart LR
    A[Agent runs and human corrections] --> B[Capture sessions via hooks or API]
    B --> C[Curate durable knowledge]
    C --> D[Retrieve knowledge or package skills]
    D --> E[Use in the next agent run]
    E --> A

Try Stash · Read the docs

For CLI setup, local development, and self-hosting, see Running this repository.

How it works

1. Capture experience. Hooks for coding agents record prompts, tool calls, and responses when session recording is enabled. Use the SDK or API to send events from your own agents.
2. Extract durable lessons. A scheduled curator reads new sessions and source material, then updates linked pages in your Memory wiki. The knowledge stays available after the original session ends.
3. Make lessons reusable. Agents search and read that knowledge through the CLI, MCP, API, or virtual filesystem. You and your agents can package related instructions and files into a Skill: a folder containing a SKILL.md.
4. Carry them into future runs. Install skills into your agent with stash skills install. Installed skills auto-update at session start, so changes to shared instructions can reach the next run without changing the underlying model's weights.

Example: a correction becomes a reusable instruction

Illustrative workflow:

Stage	What happens
Trace	An agent proposes a database migration. The reviewer points out that it would discard existing customer data.
Durable lesson	Record the project rule: schema changes must migrate existing data forward.
Reusable skill	Package a migration checklist that requires a data migration and verification that existing records survive.
Next run	The agent loads the checklist while planning another schema change. Reviewers check whether it applied the lesson.

The output is inspectable knowledge and instructions that another agent can read, use, and revise. Whether they improve results should be checked on subsequent tasks.

In an internal experiment, we measured a 49% speedup for long-running Claude Code instances using Stash. See the experiment for its setup and results.