Delimit

@delimit-ai

Visit Server

a month ago

Stop re-explaining your codebase every session. Delimit is the universal governance layer for AI coding assistants — persistent memory, tasks, and policy enforcement that works across Claude Code, Codex, Cursor, and Gemini CLI. 180+ MCP tools across 5 domains: governance (lint, diff, policy, semver), context (memory, ledger, sessions, handoffs), shipping (deploy, publish, rollback, changelog), observability (metrics, logs, alerts, status), and orchestration (multi-model deliberation, agent dispatch, swarm triggers). Core capabilities: 27-type deterministic breaking change detection for OpenAPI specs. Policy enforcement with strict/default/relaxed presets plus custom YAML rules. Cross-model session continuity — switch between Claude, Codex, Gemini, and Cursor without losing context. Multi-model deliberation where AI models debate until consensus. Git hooks, CI gates, and pre-commit governance. Zero-config onboarding with auto-detection of frameworks, specs, and test suites. Free tier includes API governance, persistent ledger, zero-spec extraction, and project scanning. Pro adds deliberation, security audit, test verification, encrypted vault, deploy pipeline, and agent orchestration. Install: npx delimit-cli setup

Overview Tools Comments

Overview

The problem with AI coding assistants

Every time you start a new session, you re-explain your codebase. Every time you switch between Claude Code and Codex, you lose context. Every time an API spec changes, nobody catches it until production breaks.

Delimit fixes all three.

One workspace across every model

Your tasks, memory, and governance policies persist across Claude Code, Codex, Cursor, and Gemini CLI. Start a task in Claude, continue it in Codex, finish it in Gemini. The ledger tracks everything.

27-type breaking change detection

Not AI inference — deterministic rules. Endpoint removed, type changed, required field added, security scheme dropped. Same input always produces the same result. Catches what code review misses.

Governance that ships with you

Policy presets (strict/default/relaxed) or custom YAML rules. Pre-commit hooks block breaking changes locally. GitHub Action blocks them on PRs. The same engine runs everywhere.

180+ MCP tools across 5 domains

Govern — lint, diff, policy, semver, security audit
Context — memory, ledger, sessions, cross-model handoffs
Ship — deploy, publish, rollback, changelog, evidence
Observe — metrics, logs, alerts, drift detection
Orchestrate — multi-model deliberation, agent dispatch, swarm triggers

Multi-model deliberation

Ask a hard question, get consensus from multiple AI models debating each other. Free tier uses Gemini Flash + GPT-4o-mini. BYOK for any model.

Zero-config start

npx delimit-cli setup

Detects your framework, finds your specs, installs governance, configures your AI assistants. One command.

Links

Server Config

{
  "mcpServers": {
    "delimit": {
      "type": "stdio",
      "command": "python3",
      "args": [
        "~/.delimit/server/ai/server.py"
      ],
      "cwd": "~/.delimit/server",
      "env": {
        "PYTHONPATH": "~/.delimit/server"
      }
    }
  }
}

Build with ShipAny.