This gives Claude persistent memory across coding sessions so it can pick up where it left off, coordinate multi-step tasks, and queue up items that need human approval before proceeding. Think of it as a stateful layer on top of Claude's otherwise stateless interactions. You'd reach for this when working on longer projects where context retention matters, or when you want explicit human-in-the-loop gates before Claude executes certain operations. It runs over stdio or SSE, so you can integrate it locally or hit the hosted endpoint at usemeridian.us. Solves the "wait, didn't we already discuss this?" problem that crops up in extended AI pair programming sessions.
Claude Code has no memory between sessions. Meridian fixes that.
Open-source MCP server for persistent AI session memory — shared task log, pinned decisions, human-in-the-loop queue, and tiered handoffs. Works with Claude Code, Cursor, Cline, Claude Desktop, or any MCP client.
Every AI coding session boots blind. You re-explain the architecture, re-describe the constraints, re-list what's been tried. When context fills up mid-task, everything is lost. This is context debt — and it compounds.
Meridian gives your sessions shared memory. They see the same task log, the same pinned decisions, the same goal state. When context fills up, a new session resumes from a compressed handoff in seconds. No copy-paste, no re-explaining from scratch.
A local MCP server every AI session connects to. They share goal state, see each other's task log, and resume from a compressed handoff when context fills up.
Two ways to run Meridian:
Linux / macOS:
git clone https://github.com/meridianmcp/Meridian
cd Meridian
./install.sh
pixi run start
Windows (PowerShell):
git clone https://github.com/meridianmcp/Meridian
cd Meridian
.\install.ps1
pixi run start
Dashboard opens at http://localhost:7878. Data persists in ./data/meridian.db.
Drop a .mcp.json at your project root.
Hosted (no install) — generate an API key at usemeridian.us/settings:
{
"mcpServers": {
"meridian": {
"type": "http",
"url": "https://usemeridian.us/mcp",
"headers": { "Authorization": "Bearer sk_meridian_YOUR_KEY_HERE" }
}
}
}
Self-host (from source):
{
"mcpServers": {
"meridian": {
"command": "pixi",
"args": ["run", "python", "-m", "meridian", "--mcp"],
"cwd": "/absolute/path/to/Meridian"
}
}
}
Same JSON snippet — both clients read .mcp.json from the project root.
Add the same mcpServers block to:
%APPDATA%\Claude\claude_desktop_config.json~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop. New chats have Meridian tools.
Use dnakov/claude-mcp — included as a submodule — to bridge claude.ai to your local Meridian server:
git clone --recurse-submodules https://github.com/meridianmcp/Meridian
chrome://extensions and enable Developer modeextensions/claude-mcphttp://localhost:7878/mcpAll 54+ Meridian tools (checkpoint, log_task, pin_decision, etc.) are now available directly in claude.ai planning chat. No copy-pasting session output.
Sign in at usemeridian.us → Settings → MCP client setup → Generate API key → Copy config.
Or manually:
{"mcpServers":{"meridian":{"type":"http","url":"https://usemeridian.us/mcp","headers":{"Authorization":"Bearer sk_meridian_YOUR_KEY_HERE"}}}}
claude.ai (browser) users: install the dnakov/claude-mcp Chrome extension, then visit usemeridian.us/install-mcp for a step-by-step setup guide with one-click copy buttons.
Get your API key at usemeridian.us/settings after sign-in. Free tier: 30 days, no card, full features.
http://localhost:7878 — sessions, tasks, sprint board,
swimlane timeline, HITL queue, pinned decisions.start_session, log_task, claim_task, set_decision,
pin_decision, request_hitl, generate_handoff, and ~50 more.claim_file can claim a single class or
function (parsed with ast / tree-sitter) so two sessions edit the same file
safely; an overlapping claim is blocked with the free symbols listed.board_change signal, no interruption.request_hitl can flag a safe-default option the
dashboard highlights; Enter submits it, number keys pick others.read_file,
list_files, search_code, git_log, get_commit injected automatically. No extra install.> start_session(project_id="meridian", session_name="feature-x")
✓ session registered · sprint loaded · 12 active tasks
> get_tasks(project_id="meridian", limit=5)
[DONE] backend / wire decisions_pinned table
[PENDING] frontend / add notes vtab (claimed by session-2)
> claim_task(task_id="a1f3...")
✓ claimed — other sessions skip this one
State lives in data/meridian.db (SQLite) or a Postgres URL via MERIDIAN_DB_URL.
No cloud required for local use.
Point MERIDIAN_DB_URL at a shared Postgres (Neon free tier works great). Every
teammate runs their own local Meridian against the same DB — instant shared
sessions, no Meridian server in the cloud.
One command wires Claude Code and Codex to Meridian. Every session start injects your project context automatically. Every session end snapshots completed work and writes a delta handoff.
Mac/Linux:
curl -fsSL https://usemeridian.us/hooks.sh | bash
Windows:
irm https://usemeridian.us/hooks.ps1 | iex
Prompts for your Meridian server URL (default http://localhost:7878), then opens
your browser to connect this machine — no project ID or API token to paste. Writes
to ~/.claude/settings.json (Claude Code) or ~/.codex/config.toml (Codex). After
setup, every session automatically:
POST /hooks/session-start → injects goal, sprint items,
recent tasks, and pinned decisions into the session context via additionalContext.POST /hooks/stop → runs auto_capture and writes a delta
handoff so the next session resumes from where this one ended.No more manual start_session() calls. No lost work when context fills.
| Standard | Pro | |
|---|---|---|
| Price | $20/mo | $49/mo (waitlist) |
| Storage | 1 GB included | 10 GB included |
| Compute | 2 CU · 100 hrs/mo | 4 CU · 300 hrs/mo |
| Environments | 1 | prod / staging / dev |
| Bring your own Postgres | ✓ | ✓ |
| OAuth + email magic link | ✓ | ✓ |
| Extra storage | $0.50 / GB-month | $0.50 / GB-month |
| Support | Priority |
30-day free trial · no card required
MSL-1.0 — free for local and internal use at any team size. Paid license required if you host Meridian as a service for others. Converts to MIT after 6 years.
For licensing questions: hello@usemeridian.us
Built by @ajc3xc
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent