delimit
One workspace for every AI coding assistant. Governance tools for API lint, diff, persistent ledger, multi-model deliberation, security audit, and test verification. Works with Claude Code, Codex, Cursor, and Gemini CLI.
README
</> Delimit
One workspace for every AI coding assistant. Switch models, not context.
Your tasks, memory, and governance carry between Claude Code, Codex, and Gemini CLI. Persistent ledger, API breaking change detection, security audit, multi-model deliberation — all shared across assistants.
GitHub Action
Add to any repo with an OpenAPI spec:
name: API Contract Check
on: pull_request
jobs:
delimit:
runs-on: ubuntu-latest
permissions:
pull-requests: write
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- uses: delimit-ai/delimit-action@v1
with:
spec: api/openapi.yaml
That's it. Delimit auto-fetches the base branch spec, diffs it, and posts a PR comment with:
- Breaking changes with severity badges
- Semver classification (major/minor/patch)
- Step-by-step migration guide
- Policy violations
View on GitHub Marketplace → · See a live demo (23 breaking changes) →
Example PR comment
Breaking Changes Detected
Change Path Severity endpoint_removed DELETE /pets/{petId}error type_changed /pets:GET:200[].id(string → integer)warning enum_value_removed /pets:GET:200[].statuswarning Semver: MAJOR (1.0.0 → 2.0.0)
Migration Guide: 3 steps to update your integration
CLI + MCP Toolkit
Governance tools for AI coding assistants (Claude Code, Codex, Cursor, Gemini CLI):
npx delimit-cli setup
No API keys. No account. Installs in 10 seconds.
CLI commands
npx delimit-cli lint api/openapi.yaml # Check for breaking changes
npx delimit-cli diff old.yaml new.yaml # Compare two specs
npx delimit-cli explain old.yaml new.yaml # Generate migration guide
npx delimit-cli init --preset strict # Initialize policies
npx delimit-cli doctor # Check setup health
What the MCP toolkit adds
When installed into your AI coding assistant, Delimit provides:
- API governance -- lint, diff, policy enforcement, semver classification
- Test verification -- confirms tests actually ran, measures coverage
- Security audit -- scans dependencies, detects secrets and anti-patterns
- Persistent ledger -- tracks tasks across sessions, auto-creates items from governance
- Multi-model consensus -- Grok, Gemini, and Codex debate until they agree
- Zero-spec extraction -- generate OpenAPI specs from FastAPI, Express, or NestJS source
What it catches
10 categories of breaking changes:
| Change | Example |
|---|---|
| Endpoint removed | DELETE /users/{id} disappeared |
| HTTP method removed | PATCH /orders no longer exists |
| Required parameter added | New required header on GET /items |
| Field removed from response | email dropped from user object |
| Type changed | id went from string to integer |
| Enum value removed | status: "pending" no longer valid |
| Response code removed | 200 OK response dropped |
| Parameter removed | sort query param removed |
| Required field added to request | Body now requires tenant_id |
| Format changed | date-time changed to date |
Detection is deterministic — rules, not AI inference. Same input always produces the same result.
Policy presets
npx delimit-cli init --preset strict # All violations are errors
npx delimit-cli init --preset default # Balanced (default)
npx delimit-cli init --preset relaxed # All violations are warnings
Or write custom rules in .delimit/policies.yml:
rules:
- id: freeze_v1
name: Freeze V1 API
change_types: [endpoint_removed, method_removed, field_removed]
severity: error
action: forbid
conditions:
path_pattern: "^/v1/.*"
message: "V1 API is frozen. Changes must be made in V2."
Supported formats
- OpenAPI 3.0 and 3.1
- Swagger 2.0
- YAML and JSON
Links
- delimit.ai -- homepage
- Docs -- full documentation
- GitHub Action -- Marketplace listing
- Quickstart -- try it in 2 minutes
- npm -- CLI package
- Pricing -- free tier + Pro
MIT License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。