contextstream - shared project memory for ai coding agents
About ContextStream
An MCP server that gives your AI coding agents one shared project memory. It captures decisions, corrections and conventions while you work, then loads the relevant slice into the next session, so Claude Code, Cursor, Codex, Cline and Windsurf start warm instead of asking you to re-explain the architecture every time. A Knowledge Atlas links those decisions back to the code they affect.
Key Capabilities
One memory that follows you between Claude Code, Cursor, Codex, Cline and Windsurf over MCP
Captures decisions and corrections as you work rather than asking you to write documentation
Knowledge Atlas links a decision to the code it touches, so an agent can see blast radius before editing
Semantic and intent-aware search across the repo and the decisions behind it
Team memory means a new hire starts with the context the team already built
Free tier is a real tier, not a trial: 3,000 credits a month, no card
Standout Features
One Memory, Every Tool
The MCP server is the whole trick: the same project memory is readable from Claude Code, Cursor, Codex, Cline and Windsurf, so switching tools does not reset what the agent knows.
Knowledge Atlas
A graph tying decisions and lessons to the code, docs and tasks they affect, so an agent can weigh impact before it edits rather than after review catches it.
Intent-Aware Search
Semantic search across the repository and the reasoning behind it, with several modes, rather than grep over file contents.
Team Memory
Team plans pool 200,000 credits per paid seat and share the workspace, so a new hire inherits the context the team already accumulated.
A Real Free Tier
Starter is free forever with 3,000 credits a month, one user, five workspaces and fifteen projects, and takes no credit card.
Perfect for
Compare ContextStream
Community Buzz
Community Buzz
No recent posts yet
We are monitoring X for fresh discussions about ContextStream.
Similar Tools to ContextStream
Conductor
macOS app for running Claude Code, Codex, Cursor, and OpenCode side by side, each in its own isolated workspace, without wrangling git worktrees by hand. You bring your own agent subscriptions and keys. The paid Conductor Cloud tier moves those workspaces into Vercel sandboxes so agents keep running after you shut the laptop, and adds shared multiplayer workspaces plus an API.
Orca
Open-source Agent Development Environment for running a fleet of AI coding agents at once. Every task gets its own git worktree, its own agent terminal, and its own browser tab, so you can fan one prompt across several agents, compare the diffs, and merge the winner. It drives roughly 30 CLI agents you already pay for, including Claude Code, Codex, OpenCode, Cursor and Copilot, and ships on macOS, Windows, Linux, iOS and Android.
Parallel Code
Free, open-source desktop app that dispatches AI coding agents in parallel, each in its own git worktree. It runs the real CLI agents you already trust (Claude Code, Codex, Gemini) side by side, then lets you review the diffs, merge the wins, and toss the rest.
Vibe Kanban
Open-source kanban board for orchestrating AI coding agents. Plan tasks as issues, run Claude Code, Codex, or Gemini CLI in isolated git worktrees, review diffs inline, and open pull requests from one local UI. The company behind it (bloop) shut down in April 2026, but the project lives on as community-maintained open source and local workspaces keep working.
Google AntiGravity
Google's agentic development platform, now split across four surfaces: the Antigravity IDE (VS Code fork), Antigravity 2.0 standalone desktop, the Go-based Antigravity CLI, and a Python SDK for custom agents.
Hermes Agent
Self-hosted autonomous agent from Nous Research with a built-in learning loop. Creates skills from experience, persists memory across sessions, and runs 24/7 on your own hardware with sandboxed terminals and messaging-app gateways.
ready to try contextstream?
go to the official site and judge ContextStream yourself.
try contextstream now