stashai

What it is and what it does

Stash is a knowledge-base platform designed to give coding agents persistent, cross-session memory. It ingests agent session transcripts, files, and data from a wide range of sources—GitHub repos, Google Drive, Gmail, Slack, Notion, Linear, Jira, Asana, Granola, and others—and stores them in a searchable, agent-native format. Agents can query this knowledge base via a CLI, MCP server, REST API, or virtual filesystem shell, so every agent run has context about every previous session you've created.

The package provides a CLI (`stashai`) that handles authentication, session recording, source integration, and agent setup. It also runs an MCP server with approximately 70 read/write tools, allowing agents to search, read, and write to the knowledge base in real time. A built-in curator can automatically compile new sessions and files into linked wiki pages, and a Skills system lets you package and share reusable knowledge folders. The tool is designed for teams running long-lived or autonomous coding agents, where duplicating work across sessions is costly and context loss is a real problem.

Use it for:

• Avoid re-solving the same bug: ask your agent if it has tackled a memory leak or similar issue before and retrieve the transcript of what was attempted.
• Track work across agents and machines: maintain a persistent log of what every coding agent has done, not just sessions on the current machine.
• Build living documentation: let agents write and update ADRs, design notes, and runbooks as they work, keeping them current without manual sync.
• Recover lost context: search for why a decision was made (e.g., why a timeout was set to 30s) without relying on git history or scattered notes.
• Share knowledge between teammates: publish a Skill (a folder with pages and tables) so other agents and team members can fork or follow it.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Stash is a CLI and MCP server that creates a persistent, agent-accessible knowledge base by ingesting sessions, files, and data from GitHub, Drive, Gmail, Notion, Slack, Linear, Jira, Asana, Granola, and other sources, then exposes them to coding agents via search, virtual filesystem, and REST API.

Yes, if you run coding agents regularly and want to avoid duplicating work across sessions. Stash is actively maintained, has low install friction, and solves a real problem—agents can only access transcripts from their current machine by default. MIT license is permissive. Beta status means the API may shift, but the core functionality (session recording, multi-source search, MCP integration) is documented and in use. Start with `stash signin` to see if the setup and agent detection work for your toolchain.

Install

stashai on PyPI

pip install stashai

uv add stashai

poetry add stashai

Installing stashai

Before you install

Low install friction with a pure Python wheel and six runtime dependencies (typer, httpx, rich, questionary, mcp, filelock). Active maintenance: last commit 2026-08-14, version 0.1.364 released 2026-08-10, and repo shows 313 stars. Beta status (Development Status :: 4) is appropriate for a young project in active development.

License in practice

MIT license (permissive) means you can use, modify, and distribute Stash freely in commercial and private projects with minimal restrictions — only attribution and license inclusion required.

Quickstart

# Install via uv
uv tool install stashai

# Authenticate and set up
stash signin

# Query your knowledge base
stash vfs ls /
stash search "your query here"

Requires Python 3.11 or later. First run (`stash signin`) opens a browser for authentication and walks through setup including session recording opt-in and agent selection.

Verify before relying

• Whether the 49% speedup claim for Claude Code is reproducible across different codebases and agent configurations.
• Exact scope and latency of federated search across all connected sources in a typical multi-source setup.
• Self-hosted deployment requirements (Docker, resource footprint, maintenance burden) beyond the docker-compose example.
• Data retention, backup, and disaster-recovery guarantees for agent sessions and imported knowledge.
• Whether MCP server (~70 tools) is fully documented and stable across different agent implementations.

Package facts

Evidence: stashai-0.1.364-py3-none-any.whl

Keywords: stash, ai, agents, coding, memory, cli

Tags

More Python Modules packages

Further reading