OpenGAP

A Git-native CLI standard for defining, validating, and exporting portable AI agents.

Stars
★ 2.9k
Last updated
2mo ago
License
MIT
Primary language
TypeScript

At a glance

Works with
Universal · cross-platformCodex · Claude Code · OpenAI API
You'll need
Node.js >= 18npmGitShell / CLINetwork accessLocal filesystemMCP Server
Typical use
An engineering team that wants to keep a code-review agent in Git and run opengap validate in CI on every change.
Main limitation
Only agent.yaml is documented as having a strict schema; the quality and completeness of the other convention-based files remain a team responsibility.

What does this agent do, and when should you use it?

OpenGAP, or Git Agent Protocol, is a Git-native standard for agent definitions plus its reference CLI. A minimal agent consists of an agent.yaml manifest and a SOUL.md identity file, with optional rules, skills, tool schemas, workflows, memory, hooks, compliance artifacts, and recursive sub-agents. Its CLI scaffolds templates, validates definitions, displays metadata, imports selected formats, and exports targets including system prompts, Claude Code files, and OpenAI Agents SDK Python code. It captures the identity layer—prompts, rules, roles, model preferences, and tool schemas—while orchestration graphs, live tool execution, memory I/O, and iterative loops remain the responsibility of the destination runtime.

After installation, the opengap CLI (with gitagent retained as a compatibility alias) can scaffold minimal, standard, full, and llm-wiki definitions through opengap init --template. opengap validate checks a definition against the specification, while opengap validate --compliance checks regulatory and segregation-of-duties configuration; opengap audit produces a compliance checklist report. opengap export --format <fmt> turns repository definitions such as agent.yaml and SOUL.md into adapter-specific output, while opengap import --from <fmt> <path> supports claude, cursor, crewai, and opencode imports, and opengap run runs a definition from a Git repository or local directory through an adapter. YAML files in workflows/ can describe deterministic skill:, agent:, and tool: steps with depends_on ordering, templated inputs, conditions, prompts, and failure-notification settings.

  1. An engineering team that wants to keep a code-review agent in Git and run opengap validate in CI on every change.
  2. An agent owner who needs one reviewed set of identity files and tool schemas exported to Claude Code, OpenAI Agents SDK, or a generic system prompt.
  3. A financial-services team that needs to declare maker/checker conflicts, human supervision, recordkeeping, and audit controls in agent configuration.
  4. A platform team that wants to reuse a base agent, skills, or sub-agent definitions through extends and dependencies.
  5. A developer migrating the identity layer of a Claude, Cursor, CrewAI, or OpenCode agent into a versioned repository.

How do you install or deploy this agent?

Prerequisites are Node.js >= 18, npm, and Git. Install globally:

npm i -g @open-gitagent/opengap

Use opengap after installation; gitagent is installed as a backward-compatible alias. No API credential is documented as a prerequisite for creating, validating, or exporting an agent definition.

How do you use this agent?

Create and inspect a first definition inside a Git repository:

opengap init --template standard
opengap validate
opengap info
opengap export --format system-prompt

Keep agent.yaml and SOUL.md for the minimum valid definition. To run a definition directly:

opengap run ./my-agent --adapter lyzr

To keep the agent definition separate from the target workspace:

opengap run --dir ./agents/reviewer --workspace ~/code/my-app --adapter claude -p "Review this repository"

What are this agent's strengths and limitations?

Pros
  • Uses commits, branches, diffs, tags, and pull requests as the lifecycle for agent definitions, enabling rollback and line-level auditability.
  • Separates manifests, identity, hard rules, duties, skills, tools, and workflows into reviewable repository assets.
  • Provides documented init, validate, audit, import, export, run, and skills commands alongside a broad adapter list.
  • Includes explicit financial-compliance and segregation-of-duties structures, including role conflicts, required handoffs, and strict or advisory enforcement.
Limitations
  • Only agent.yaml is documented as having a strict schema; the quality and completeness of the other convention-based files remain a team responsibility.
  • Exports do not carry over runtime orchestration, live tool execution, memory I/O, or iterative loops, so destination-runtime work is still required.
  • The CLI requires Node.js >= 18, npm, Git, and local filesystem access; resolving Git dependencies and running from remote repositories also involves network access.
  • The supplied documentation lists adapters but does not establish feature parity, authentication requirements, or production guarantees for each adapter.

How does this agent compare with similar options?

Relative to runtime frameworks named in the documentation—such as Claude Code, OpenAI Agents SDK, CrewAI, and LangGraph—OpenGAP focuses on extracting and versioning the identity layer, rules, roles, and tool schemas rather than replacing runtime orchestration or execution.

Key facts side by side with the most closely related agents.

Agent Source review Stars Updated Language Full support on
OpenGAP This agent 51 · Major gaps ★ 2.9k 2mo ago TypeScript Codex · Claude Code · OpenAI API
DACA Agentic AI Learning Stack 38 · Major gaps ★ 4.4k 11mo ago Jupyter Notebook OpenAI API
Agency Swarm 45 · Major gaps ★ 4.6k 1d ago Python OpenAI API
Gitagent 44 · Major gaps ★ 702 1mo ago Rust OpenAI API · Claude API

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
51/ 100 5-point scale 2.6 / 5
Trust 11/29
Reliability 8/14
Adaptability 12/18
Convention 10/18
Effectiveness 7/13
Verifiability 3/8
Why each dimension lost points
Trust11 / 29 · 1.9/5

Evidence shows: permission controls (SOD roles), user confirmation (human-in-the-loop), data flow transparency (git diff/blame), sensitive data handling (.env and .gitignore), dependency security (npm dependencies), external effects (git operations), rollback (git versioning), and source attribution (git blame). However, these are documented, not verified by code, and the permission model may be overly complex without clear least privilege. Deductions: lack of execution evidence, potential over-permissioning.

Reliability8 / 14 · 2.9/5

Evidence shows: self-consistent spec (agent.yaml, SOUL.md), clear dependency list, but failure messages not detailed. Deductions: insufficient failure handling documentation, dependency availability unverified.

Adaptability12 / 18 · 3.3/5

Evidence shows: targets multiple audiences (developers, compliance), defines capability boundaries (skills, tools), triggers (workflows), environment fit (multiple adapters). Deductions: trigger precision and boundary definitions are brief.

Convention10 / 18 · 2.8/5

Evidence shows: clear information architecture (directory structure), install notes (npm install), naming stability (opengap/gitagent alias), rich examples (examples/), MIT license, version number, maintenance responsibility (author). Deductions: known limitations not explicit, changelog missing, maintenance responsibility only author name.

Effectiveness7 / 13 · 2.7/5

Evidence shows: usable outputs (multiple export formats), high marginal value (solves framework fragmentation), cost-benefit not quantified. Deductions: no data for cost-benefit.

Verifiability3 / 8 · 1.9/5

Evidence shows: concrete examples and patterns, but lack independent verification, facts vs inferences not clearly separated. Deductions: claims are assertions without test results.

Risks and how to mitigate them
  • Compliance claims (FINRA, SEC) are unverified and may be marketing assertions.
  • Permission model (SOD) may be overly complex and could violate least privilege in practice.
  • Dependency security not audited, potential known vulnerabilities.
  • Publisher identity unverified, maintenance responsibility unclear.
Evidence confidence: Low Reviewed Aug 09, 2026 Reviewed revision d7a8e2edb54b
See the full review method →

FAQ

What is the minimum agent definition?
agent.yaml and SOUL.md are the only required files; the README identifies them as the manifest and identity, respectively.
Can it target Claude Code or Codex?
It documents export to a Claude Code-compatible CLAUDE.md and export to OpenAI Codex CLI instructions. Both are listed as export-only adapter targets.
Does it execute every workflow by itself?
SkillsFlow is documented as deterministic YAML in workflows/. Running occurs through the CLI run command and a selected adapter, while live execution remains part of the target runtime boundary.
Is a particular model or cloud provider required?
No specific provider is required by the documented minimum definition. The standard is described as framework-agnostic, and agent.yaml may express a preferred model without making one mandatory.
What are the license and documented costs?
The repository is MIT licensed. The supplied material does not state pricing for the npm package, model usage, hosting, or third-party adapters.
View on GitHub ↗ Install ↓

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related agents