Sandbox
@Intina47/context-sync

Local memory MCP server for coding agents

Context Sync adds a persistent memory layer to AI coding tools through MCP. It stores project identity, decisions, file structure, git context, and optional Notion lookup so your agent can retrieve context later.

192 stars18 forksTypeScriptUpdated 5mo ago
Who it's for

Builders who want their agent to remember project context across sessions.

What it delivers

You can resume work with remembered context instead of re-explaining the project every time.

What it does

Project memory

Stores project identity, stack, decisions, constraints, and other context with `set_project`, `remember`, and `recall`.

Structured file exploration

Lets an agent inspect files and folders with `structure`, `read_file`, and `search`.

Git-aware context

Captures repo state and supports `status`, `context`, `hotspots`, `coupling`, `blame`, and `analysis`.

Automatic git hooks

Installs `post-commit`, `pre-push`, `post-merge`, and `post-checkout` hooks for context capture when `set_project` runs inside a git repo.

Optional Notion lookup

Adds read-only Notion search and page reading through the `notion` tool.

Auto-configuration

Configures supported tools during global install and provides manual setup guidance when auto-config fails.

How to get it

  1. 1Install globally
    npm install -g @context-sync/server
  2. 2Run the setup wizard if you want Notion integration
    context-sync-setup
  3. 3or
    npx context-sync-setup

README

Context Sync

Local-first project memory for AI coding tools over MCP.

Context Sync gives an agent a persistent memory layer for a codebase:

  • project identity and tech stack
  • active work, decisions, constraints, and caveats
  • structured file exploration
  • git-aware context
  • optional read-only Notion lookup

Context Sync

What It Does

Context Sync is built for session continuity. Instead of relying on a model to remember earlier conversations, it stores the project context that matters and makes it retrievable through a small MCP tool surface.

The current core tools are:

  • set_project
  • remember
  • recall
  • read_file
  • search
  • structure
  • git
  • notion

Install

Install globally:

npm install -g @context-sync/server

Auto-configuration runs during global install. After install, restart your AI tool.

If you install locally instead of globally, auto-config does not run. Use the manual config guide in docs/CONFIG.md.

Verify

Check that context-sync appears in your MCP tool list:

  • Claude Desktop: open the tools list
  • Cursor: open the tools list
  • VS Code / Copilot Chat Agent mode: check tools
  • Continue.dev: open the Continue panel
  • Codex CLI: codex mcp list
  • Claude Code: claude mcp list

If auto-config fails, use docs/TROUBLESHOOTING.md and docs/CONFIG.md.

Optional Notion Setup

Run the setup wizard if you want Notion integration:

context-sync-setup

or:

npx context-sync-setup

Notion support is intentionally read-only at the tool surface:

  • notion({ action: "search", query: "..." })
  • notion({ action: "read", pageId: "..." })

First-Time Workflow

Start every new session by setting the project first:

1. set_project({ path: "/absolute/path/to/project" })
2. recall()
3. structure({ depth: 2 })
4. read_file({ path: "src/index.ts" })
5. remember({ type: "decision", content: "Use SQLite for local storage" })

Recommended pattern:

  • set_project once per project/session start
  • recall to recover context
  • structure and search to explore
  • read_file for focused inspection
  • remember when something should survive the current session

Git Integration

When you run set_project inside a git repository, Context Sync can install hooks for automatic context capture.

Installed hooks:

  • post-commit
  • pre-push
  • post-merge
  • post-checkout

Hooks are marked with Context Sync Auto-Hook, and existing hooks are backed up first.

The git tool supports:

  • status
  • context
  • hotspots
  • coupling
  • blame
  • analysis

Data And Config

Default locations:

  • Database: ~/.context-sync/data.db
  • Config: ~/.context-sync/config.json
  • Install status: ~/.context-sync/install-status.json

Custom database options:

  • CLI: context-sync --db-path /absolute/path/to/db
  • Env var: CONTEXT_SYNC_DB_PATH

See docs/DATA.md for storage details.

Supported Platforms

  • Claude Desktop
  • Cursor
  • VS Code + GitHub Copilot
  • Continue.dev
  • Zed
  • Windsurf
  • Codeium
  • TabNine
  • Codex CLI
  • Claude Code
  • Antigravity

Docs

Files in the repo

Repository payload16 top-level entries
  • .github
  • assets
  • bin
  • docs
  • src
  • .gitignore
  • .npmignore
  • AGENTS.md
  • ARCHITECTURE.md
  • image.png
  • LICENSE
  • package-lock.json
  • package.json
  • README.md
  • RUST-MIGRATION-ASSESSMENT.md
  • tsconfig.json

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k