Community

Built in the open,
for everyone

Admina is a community project. Every issue, PR, discussion, and star makes a difference. We respond to all contributions as soon as possible.

How to contribute

All contributions are welcome, from bug fixes to new governance domains and plugins. Here are the most impactful ways to help.

01

Report bugs and edge cases

Run Admina in your environment and share what you find. Real-world edge cases improve governance quality for everyone.

02

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.

03

Write connectors

LangChain, CrewAI, n8n, OpenClaw, and Cheshire Cat connectors ship with every release, alongside seven model-provider adapters and β€” since v0.11.0 β€” an OpenAI-compatible governance gateway. New framework integrations are always welcome β€” see the plugin system's 9 interfaces.

04

Improve documentation

Clear docs are as important as good code. Fix typos, improve examples, translate content, or write a tutorial.

05

Share benchmarks

Run the benchmark suite on your hardware and share the results. Performance data from diverse environments strengthens the project.

06

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.

Why "Admina"?

The name

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.

Pronunciation
À·dmiΒ·na /ˈad.mi.na/

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.

Changelog

Past releases β€” what shipped, when, and why. The full release history with per-version details is maintained in the source repository, alongside the code it documents.

Roadmap

Where Admina is going next. 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 forward plan in ROADMAP.md.

v0.11.0 β€” 2026-07-15
Streaming governance & an OpenAI-compatible gateway
  • SDK streaming. GovernedModel.stream() yields PII-redacted deltas as an async iterator; the new StreamRedactor holds back a trailing window (sized by the stream() kwarg stream_window_chars, default 64) so an entity split across delta boundaries is still redacted. A blocked prompt yields no deltas and reports action="BLOCK" without raising; the full outcome lands in last_stream_result
  • Streaming on the adapter contract via BaseModelAdapter.send_stream() β€” real incremental streaming for the OpenAI, Ollama, vLLM, and Anthropic adapters; Mistral, Gemini, and Bedrock use the base single-chunk fallback
  • OpenAI-compatible governance gateway β€” POST /v1/chat/completions (streaming and non-streaming) plus GET /v1/models, forwarding to a configurable upstream (ADMINA_GATEWAY_UPSTREAM) while the canonical pipeline runs inline. A blocked request returns a synthetic completion (or SSE stream) with finish_reason: "content_filter" instead of a raw HTTP error, and every request is written to the forensic log. Protected by the existing credential check
  • Microsoft Presidio as a selectable PII engine (ADMINA_PII_ENGINE=presidio, behind the [presidio] extra). Detection only β€” Admina keeps its own masking, so the output format is identical across engines. The default engine is unchanged (spacy-regex)
  • Breaking: /api/v1/validate returns action="REDACT" in place of the former "MODIFY" β€” a clean rename with no compatibility shim, permitted under the pre-1.0 posture
  • Signed forensic chain state. _chain_state.json can be signed with HMAC-SHA256 (ADMINA_FORENSIC_STATE_KEY, signature in a .sig sidecar); a missing or invalid signature is treated as untrusted and the chain is reconstructed from the immutable records
  • Configurable guard fail mode (ADMINA_GUARD_FAIL_MODE=open|closed, default open): under closed, an exception raised inside a governance guard turns into a BLOCK
v0.13.0 β€” Multi-tenancy & RBAC
  • 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
v0.14.0 β€” Compliance template expansion
  • 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
v1.0.0 β€” API freeze & LTS
  • 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
  • Security advisory process documented; CVE assignment workflow
  • Removal of the compatibility shims in admina/proxy/ that keep pre-0.10 imports working
🀝
Code of Conduct

Admina follows the Contributor Covenant. We're committed to a welcoming and inclusive community. All contributors are expected to uphold these standards.

Read CoC