Browse the source code, open issues, submit pull requests, and star the project.
admina-org/admina βAsk questions, share your setup, propose features, and talk to the maintainer and community.
Join discussions βFound a bug? Have a feature request? Open an issue β we respond as soon as possible.
Open an issue βHow to set up your dev environment, coding conventions, testing, and submitting PRs.
Read CONTRIBUTING.md βHow to contribute
All contributions are welcome, from bug fixes to new governance domains and plugins. Here are the most impactful ways to help.
Report bugs and edge cases
Run Admina in your environment and share what you find. Real-world edge cases improve governance quality for everyone.
Contribute injection patterns
The Agent Security firewall uses a library of regex patterns. Add new patterns for attack vectors you've encountered β each one protects all Admina users.
Write connectors
LangChain, CrewAI, n8n, OpenClaw, and Cheshire Cat connectors are shipped. New framework integrations are always welcome β see the plugin system's 9 interfaces.
Improve documentation
Clear docs are as important as good code. Fix typos, improve examples, translate content, or write a tutorial.
Share benchmarks
Run the benchmark suite on your hardware and share the results. Performance data from diverse environments strengthens the project.
Star and spread the word
A GitHub star signals to the community that this project matters. Share Admina with your team, write a blog post, or talk about it at a meetup.
Maintainer
Why "Admina"?
Admina comes from admin β administrative oversight, system governance β shaped into a name with a firm, precise sound, like a trusted system daemon always running quietly in the background.
It also echoes admina as in sysadmin β the person who manages, enforces rules, and keeps systems in order. Exactly what Admina does for AI agents.
Stress on the first syllable: Γ-dmi-na. Think of it like Γ dmin + a, not ad-mΓ-na. Three clean syllables, firm and direct β like the governance it provides.
Roadmap
Admina is pre-1.0: the public API is feature-complete and production-ready, but the stability commitment is deferred until community validation has confirmed the shape of the public surface. Releases ship when scope is ready β not on a calendar. Full plan in ROADMAP.md.
- OISG paradigm (Open Β· Intelligent Β· Secure Β· Governed) β default install scores in the adequate band (β₯ 80/100)
- SDK with 4 governed primitives: GovernedModel, GovernedData, GovernedAgent, ComplianceKit
- Plugin system: 9 interfaces with built-in reference implementations (Ollama, OpenAI, ChromaDB, MCP, REST, MinIO, spaCy+regex, GuardrailsAI opt-in, β¦)
- 5 framework integrations: LangChain, CrewAI, n8n, OpenClaw, Cheshire Cat AI
- 4-domain Rust pipeline β 6.25Β΅s median (P95 7.04Β΅s, P99 7.29Β΅s)
- Admina Score + OISG adequacy widgets on the dashboard, with live WebSocket feed
- CLI:
admina init,dev,plugin,doctor - Multi-platform wheels (Linux x86_64/aarch64, macOS x86_64/arm64) via GitHub Actions
- Bug fixes driven by early-adopter reports
- Documentation hardening: guided tutorials, troubleshooting matrix, plugin dev walkthrough
- Test-coverage expansion on edge cases surfaced after the public release
- Packaging fixes (wheel manifests, extras resolution, Docker image size)
- Model adapters: Anthropic, Mistral, AWS Bedrock, Google Gemini, native vLLM
- Microsoft Presidio as first-class PII engine alongside spaCy+regex
- Streaming-first
GovernedModelAPI with inline governance per chunk - Configurable retry / backoff on all governed primitives
- WebSocket authentication with API-key scoping
- Native Prometheus metrics endpoint with SLO panel
- Structured error taxonomy (stable error codes across proxy, SDK, REST)
- Decision cache on the injection firewall fast path
- Benchmark regression gate in CI (fail on >10% regression)
- Request-level tracing correlation SDK β proxy β upstream LLM
- Organisation / workspace isolation in the proxy
- Per-tenant quotas (rate, forensic retention, templates)
- RBAC on proxy endpoints (read / write / admin)
- OIDC auth provider as built-in plugin
- Per-tenant forensic namespace with independent hash chains
- NIS2 template (incident response, supply-chain obligations)
- ISO/IEC 42001 (AI management system controls)
- SOC 2 (Trust Services Criteria mapping)
- Cross-framework gap analysis (single control β multiple frameworks)
- Signed PDF/DOCX report export
- Plugin ABI v1 frozen with contract tests; third-party plugin certification suite
- Official client SDKs: TypeScript, Go
- Deprecation policy formalised; 18-month LTS window for the 1.0 line
- CVE assignment workflow documented