opengap
A framework-agnostic, git-native standard for defining AI agents
- 3k stars
- 354 forks
- 29 open issues
- Language: TypeScript
- License: MIT
- updated
Install
git clone https://github.com/open-gitagent/opengap && cp opengap/*.md ~/.claude/agents/- Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
- Start a new Claude Code session to load the agents.
- Delegate work to them with the Task/Agent tool or by name.
Editor's note
OpenGAP (Git Agent Protocol) is an open specification and reference CLI that turns any git repository into a portable, framework-agnostic AI agent definition. Developers structure their repo using a small set of files: a required `agent.yaml` manifest and `SOUL.md` identity document, with optional additions for rules, duties, skills, tools, workflows, knowledge, memory, and compliance artifacts. The `opengap` CLI, published to npm as `@open-gitagent/opengap`, reads this structure and exports it to runtimes including Claude Code, OpenAI, LangChain, CrewAI, and AutoGen via adapters. It integrates with Claude Code directly and supports MCP-compatible tool definitions through YAML schemas in the `tools/` directory. A standout feature is built-in segregation of duties enforcement, with a conflict matrix in `agent.yaml` that prevents a single agent from occupying incompatible roles such as both `maker` and `checker`, targeting regulated industries with FINRA, SEC, and Federal Reserve compliance requirements. Developers building multi-agent systems, compliance-sensitive applications, or reusable agent libraries across multiple frameworks are the primary audience.
18 items in this repository
Reviews code diffs and files for security vulnerabilities (OWASP Top 10), error handling, complexity, naming conventions, and performance issues. Use when the user asks to review a PR, pull request, diff, merge request, or code changes.
Creates and configures agent.yaml files, writes SOUL.md personality definitions, and sets up agent directory structures with skills, tools, and knowledge. Use when the user wants to configure an agent, create agent.yaml, write SOUL.md, set up agent directory structure, or customize agent settings.
Reviews financial documents (prospectuses, ADVs, marketing materials) for FINRA 2210 compliance, required disclosures, and balanced presentation. Use when reviewing financial statements, audit documents, regulatory filings, or when the user mentions compliance checks, financial audits, or document verification.
Converts agent definitions between frameworks — exports to Claude Code, OpenAI, CrewAI, Lyzr, and GitHub Models formats, and imports from Claude, Cursor, and CrewAI projects. Use when the user wants to convert an agent, migrate to another framework, export to LangChain/AutoGen/CrewAI, or import from existing automation tools.
Guides installation of gitagent and creation of first agent with scaffolding, configuration, and validation. Use when the user is new to gitagent, asks how to get started, wants to install gitagent, set up their first agent, or says 'how do I start?'
Semantic search over ingested documents using RAG (LlamaIndex/ChromaDB or Foundational RAG)
Searches the SkillsMP registry, installs skills locally or globally, creates custom skills with SKILL.md frontmatter, and manages the skill lifecycle. Use when the user wants to find skills, add new capabilities, install a skill, browse available skills, create a custom skill, or manage the skills system.
Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.
Researches a topic by breaking it into subtopics, gathering factual information with reasoning, and producing a structured summary with key findings and open questions. Use when the user asks to research, investigate, look up, summarize a topic, or says 'what is known about...' or 'learn about...'
Configures and runs agents with different adapters including Claude, OpenAI, CrewAI, Lyzr, and GitHub Models. Supports local execution, remote git repos, and one-shot prompts. Use when the user wants to run an agent, switch LLM providers, configure adapter settings, or launch agents from git repositories.
Ingest a raw source document into the wiki. Reads the source, extracts key information, creates or updates wiki pages, maintains cross-references, and logs the operation. Use when the user adds a new source or says 'ingest this'.
Health-check the wiki for contradictions, stale claims, orphan pages, missing cross-references, and knowledge gaps. Use periodically or when the user says 'lint the wiki' or 'check wiki health'.
Query the wiki to answer questions. Searches wiki pages, synthesizes answers with citations, and optionally files valuable answers back as new wiki pages. Use when the user asks a question about the knowledge base.
Subagents overview
What people ask about opengap
What is open-gitagent/opengap?
open-gitagent/opengap is subagents for the Claude AI ecosystem. A framework-agnostic, git-native standard for defining AI agents It has 3k GitHub stars and its last recorded update is dated 2026-07-02.
How do I install opengap?
You can install opengap by cloning the repository (https://github.com/open-gitagent/opengap) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is open-gitagent/opengap safe to use?
Our security agent has analyzed open-gitagent/opengap and assigned a Trust Score of 87/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.
Who maintains open-gitagent/opengap?
open-gitagent/opengap is maintained by open-gitagent. The last recorded GitHub activity is dated 2026-07-02, with 29 open issues.
Are there alternatives to opengap?
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.