# MetapriseAI/OrgKernel

Open-source trust layer for AI agents — cryptographic agent identity (Ed25519), instance-scoped execution tokens, SHA-256 hash-chained audit logging, and enterprise SSO/SCIM federation. The security foundation powering every agent in the Metaprise AURA platform.

Repository: https://github.com/MetapriseAI/OrgKernel
Canonical: https://ross.abutalabs.com/products/orgkernel
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-07-06T19:46:41+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 91, release rhythm 35, longevity 11
- inputs: {"age_days": 161, "days_push": 58, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2700, forks 247 (observed 2026-08-28T04:07:11.369864+00:00)

## What it is
OrgKernel is an open-source trust layer for AI agents providing cryptographic agent identity (Ed25519), scoped execution tokens, SHA-256 hash-chained audit logging, and enterprise SSO/SCIM support. It integrates with agent frameworks like LangGraph, CrewAI, and AutoGen and persists to PostgreSQL, MySQL, or SQLite.

## Use cases
- add cryptographic identity to AI agents
- enforce scoped permissions on agent tool calls
- create tamper-evident audit logs of agent actions
- federate agent access with enterprise SSO and SCIM
- block agents from exceeding spending or authority limits
- integrate governance into LangGraph or CrewAI workflows

## When to choose
- you deploy AI agents in an organization and need verifiable identity and authorization
- you need tamper-evident audit trails for compliance
- you want permission enforcement in the execution path rather than app code
- you use LangGraph, CrewAI, or AutoGen and need a governance layer

## When to avoid
- you only need simple API-key auth for a prototype
- your stack is not Python 3.10+
- you need a fully managed SaaS governance product rather than a self-hosted library
- your agent framework is unsupported by its integrations

## Facets
- artifact type: library
- maturity: active
- function: auth, authorization, security, logging, cryptography, middleware, sdk
- domain: security, large-language-models, developer-tools, backend
- platform: python, cross-platform, self-hosted
- tags: agent-identity, ed25519, audit-trail, hash-chain, scim, sso, execution-tokens, agent-governance, trust-layer, fastapi, langgraph, crewai, autogen, ai-agents, docker

## Member repositories
- MetapriseAI/OrgKernel (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.369864+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:16:00.315310+00:00, confidence not recorded.
  - readme: https://github.com/MetapriseAI/OrgKernel (fetched 2026-08-28T04:07:11.369864+00:00, sha 20279442ad25)
- Data as of 2026-08-30T08:39:29.467469+00:00.