7 projects
openwright-core
Agent Evidence Layer — turns AI-agent runtime behavior into signed, tamper-evident, control-mapped audit evidence.
openwright-langfuse
Langfuse forwarder for OpenWright — co-ingest + openwright:* verdict back-link + evals-as-evidence.
openwright-openai-agents
OpenAI Agents SDK source connector for OpenWright — capture agent runs, tools, handoffs, and approvals as evidence.
openwright-s3
S3 checkpoint store for OpenWright — Object-Lock/WORM chain-of-custody.
openwright-postgres
PostgreSQL ledger backend for OpenWright — durable, multi-writer evidence.
openwright-github-action
GitHub-CI evidence-gate exporter for OpenWright — shift-left control gating + SARIF.
openwright-langgraph
LangGraph source connector for OpenWright — capture agent decisions, tools, and human-in-the-loop approvals as evidence.
