|
LoopGrid — Verifiable evidence for consequential AI decisions
LoopGrid is decision evidence infrastructure for consequential AI systems and agents. Explore a synthetic action workflow, inspect cryptographically signed e...
|
85 % |
|
WeaveFlow | Build inspectable agent workflows in Go
WeaveFlow is a graph runtime written in Go for building, executing, and inspecting LLM agent workflows.
|
83 % |
|
Clay - Evidence-led prospecting you can verify line by line
Evidence-led prospecting inside your AI agent.
|
82 % |
|
PhantomBuster - Evidence-led prospecting you can verify line by line
Evidence-led prospecting inside your AI agent.
|
82 % |
|
RocketReach Research
Evidence-led company research in your AI agent.
|
82 % |
|
AI adoption. Your infrastructure. Measurable value. | YABANIN
YABANIN brings AI into your business with self-hosted infrastructure, agent workflows, and hands-on implementation. Control your data, understand task costs,...
|
82 % |
|
Assevra — Find agent failures before your users do
Open-source agent evaluation with actionable findings, explicit release gates, and portable evidence. Connect captured runs, fix failing cases, and verify th...
|
82 % |
|
CauseSignal | Agentic engineering investigation
CauseSignal is an evidence-led investigation system built from governed specialist playbooks. It reconstructs incidents, defects, regressions, and risky chan...
|
81 % |
|
Traceant — Every Award, Defensible.
Traceant connects source documents, vendor responses, comparison, approval, and audit history into one evidence-native procurement decision record.
|
81 % |
|
InsightRecorder — Know exactly what happened
Reconstruct production incidents from user sessions, logs, metrics and traces — with evidence your team can trust. Stop investigating across five different t...
|
81 % |
|
SilentWitness — hypothesis-first DFIR investigator
MCP server + Pydantic AI agent that runs evidence-grounded, hash-chained, hypothesis-first DFIR investigations. Every claim locked to the tool execution that...
|
81 % |
|
Nooks - A working prospecting agent one command away
Evidence-led prospecting inside your AI agent.
|
81 % |
|
Unify GTM - A working prospecting agent one command away
Evidence-led prospecting inside your AI agent.
|
81 % |
|
phebs — static contract evidence and self-hosted code search
What does this contract change touch? phebs answers from committed source at an immutable commit — resolved callers, name matches, unresolved sites, and the...
|
80 % |
|
Promtact - reproducible verification for distributed systems
Turn rare distributed-system failures into deterministic tests your team can replay locally, in CI and inside its own infrastructure.
|
80 % |
|
SelectAgent Verify | Outcome verification for agents
Check whether an agent's intended action actually happened. SelectAgent Verify compares expected outcomes with receiving-system evidence and returns a bounde...
|
80 % |
|
Sentinel.AI — The Control Plane for AI Agents
Logging tells you what broke. Sentinel stops it before it breaks — and lets you replay from a checkpoint without restarting the pipeline.
|
80 % |
|
GroundLens — Verification infrastructure for AI systems and agents
GroundLens turns observable AI execution into policy-governed, independently verifiable evidence. Verify claims and actions, enforce execution policies, and...
|
80 % |
|
TraceDog — Observability for AI agents
Inspect AI runs, measure grounding, compare models. Open-source trace scoring and reliability UI.
|
80 % |
|
TraceMap | Evidence-backed repository maps
TraceMap is a deterministic repository indexer and contract-change impact reducer that publishes rule-backed evidence, coverage labels, and static dependency...
|
80 % |
Detected social media networks