12 projects
latenzy
Per-model LLM latency monitoring — Prometheus exporter and Grafana dashboards for Claude, OpenAI, and Gemini.
verel
The agent framework where nothing is done until a grader returns a verdict — verification + grounded perception (AgentVision eyes), compounding memory, a fleet, agent-built tooling, and agent-run CI/CD.
assaylab
Validation intelligence for CI — failure-signature RCA, flaky-vs-real classification, and attested test-selection with a verifiable confidence bound. Contract-compatible with agentsensory (pass/warn/fail + Handoff).
agentvision
Eyes for AI Agents — a machine-graded visual feedback loop coding agents consume to self-correct before claiming done.
synap-protocol
SynAP - the Synaptic Agent Protocol: a semantic control plane for inter-agent communication
citel
Knowledge/recall/grounding sense for AI agents — knowledge graph + RAG that grades citation-faithfulness and groundedness on the agentsensory verdict contract.
immel
Immune/security organ for AI agents — boundary posture, threat detection and policy-gated response on the agentsensory verdict contract.
olfel
Smell/anomaly sense for AI agents — code/log/dependency smells normalized into the agentsensory verdict contract.
actel
Hands/actuation organ for AI agents — executes effects and verifies post-conditions via the senses, on the agentsensory verdict contract.
vitel
Vitals for AI Agents — graded observability returning pass/warn/fail on metrics, SLOs and error budgets, with each finding grounded in a Metric. Sibling to AgentVision (eyes), Audel (ears) and Verel (brain).
audel
Ears for AI Agents — a machine-graded audio feedback loop coding agents consume to self-correct before claiming done.
agentsensory
Shared sensing contract for AI-agent graders — the verdict/report/intent/handoff models and the Sense protocol behind AgentVision (eyes), Audel (ears) and Verel (brain).
