ContextStream
Persistent memory and semantic search for AI coding assistants across sessions
Ads
Overview
ContextStream MCPThe production connection for your assistantPlatformCode, memory, media, and project operations ContextCode BetaOptional terminal coding agent in beta Connect your assistant Manual setup Custom MCP Connector Hosted or local Instruction files Keeping it current Troubleshooting Command reference ContextStream's production product is the MCP connection used from the assistant you already have. It is implemented by the Rust MCP server and connects Claude Code, Cursor, Codex, VS Code, and other supported clients to ContextStream's search, memory, and durable project context.
Installation
Installation instructions are not available yet.
Configuration
Configuration example is not available yet.
Capabilities
- Recall past decisions
Ask "what did we decide about retries?" and get the recorded decision from weeks ago, not a fresh opinion.
- Locate code from an index
Ask "where do we handle expired tokens?" and get files and lines from a pre-built index without reading the repository first.
- Retrieve prior session context
Ask "what were we working on last week?" and get exchanges and snapshots captured by your connected assistants across editors.
- Save durable project facts
Tell it "remember we're on Postgres, not MySQL" and have it stored as persistent context for authorized clients.
- Generate operational runbooks
Ask for a "signing-key rotation runbook" and get a maintained procedure with verification, rollback, and stop conditions.
- Hand off work to another agent
Request a scoped transfer with current state, open questions, next steps, and evidence for another assistant to continue.
Tags
- memory
- vector-search
- coding-agent
- knowledge-retrieval
Related MCP servers
Memory MCP Server
OfficialPersist assistant memory as a lightweight knowledge graph across sessions.
OpenLore
OfficialAgent-native knowledge server. Serves docs to AI agents over SSH and MCP with identity-scoped views, governed writing, and structured metadata. Single binary, zero config.
gingugu/gingugu
Persistent memory for AI coding assistants. Local SQLite, no cloud. 16 MCP tools: store, recall, search, relate, consolidate, export, and credential vault (OS keychain). Typed memories with confidence lifecycle (verified/inferred/stale/deprecated), namespaces, knowledge graph, and hybrid BM25 + semantic search via fastembed ONNX. Works with Cursor, Windsurf, Claude, and any MCP client. `pip install gingugu`
GistPad-MCP
Use GitHub Gists to manage and access your personal knowledge, daily notes, and reusable prompts. This acts as a companion to https://gistpad.dev and the [GistPad VS Code extension](https://aka.ms/gistpad).