|
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 % |
|
Lens Strata: Answers with evidence
Lens Strata is the AI platform organizations can put to work safely: search, chat, agents and automated work over your own documents, with every answer check...
|
80 % |
|
fossilize — evidence-based code documentation
fossilize documents your code from three sources of truth — the AST, the tests, and git — and refuses to assert anything it cannot prove. A trustworthy, drif...
|
80 % |
|
Hotato: voice agent regression tests and call health
Find what broke in your agent calls. Pin it and CI stays red until you fix it. Debug a broken voice-agent call in minutes: local call forensics and regressio...
|
80 % |
|
Cliewen
A verifiable thread from goal to acceptance evidence, checked before merge: Evidence-backed Intent Engineering for coding agents.
|
80 % |
|
Adjudica — Decision records for application security
Adjudica records what you decided, what evidence you relied on, and tells you when that evidence stops being true. Scanner-agnostic decision records for AppS...
|
80 % |
|
Tracevity — Check AI Agent Evidence and Catch Reconstruction Regressions
Check what an AI-agent trace can establish. Explore a GitHub effect example, run Inspect locally, and Gate releases that lose required reconstruction evidence.
|
80 % |
|
Patric Fitigau, document automation that cites its sources
Contract AI engineering: retrieval systems that cite every claim to a source file and abstain when the evidence is missing. Python, FastAPI, n8n. Available now.
|
79 % |
|
agents.cli
A publication on context engineering, closing the gap between AI coding agents and the context they don't have.
|
79 % |
|
CodeRifts — Know what may proceed. Prove why it did.
A fail-closed authorization-execution gate: one grant binds authorize, consume, target-state transition, and offline readback. Without this receipt the check...
|
79 % |
|
𓉸 EXIT Protocol — Departure Records for AI Agents
EXIT Protocol — Signed, portable, offline-verifiable departure records for AI agents. Think Carfax, but the agent signs it.
|
79 % |
|
RocketReach Research
Evidence-led company research in your AI agent.
|
79 % |
|
FactSpectra — answers your auditor can check
Grounded document intelligence: hybrid RAG with the failure mode removed — a LangGraph pipeline on Claude where every claim carries a quote verified against...
|
79 % |
|
Quick start — ChangeClause docs
Scope guard for AI-written changes. Your agent says it is done. ChangeClause checks the claim.
|
79 % |
|
TestMutant | QA Agent for Important Website and App Flows
QA coverage for fast-moving websites and software teams. Start with a URL and important flows, then add Jira, Linear, GitHub, CI/CD, and Playwright draft PRs...
|
78 % |
|
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...
|
78 % |
|
AXM -- Competes with Forgetting
AXM compiles knowledge into signed, searchable, tamper-proof shards. LLM at compile time. SQL at query time. Offline forever.
|
78 % |
|
Margyn: audit your test suite and prove which checks are hollow
Margyn finds tests that assert nothing, files git never committed and gates nothing invokes, then ships a command that reproduces every finding. Free CLI, $8...
|
78 % |
|
AEGIS · The zero-retention AI governance gateway
AEGIS is an open source AI gateway in Go. It enforces policy on every model call and writes a complete decision record that contains no prompt or response text.
|
78 % |
|
LoopCode — Repository control for long-running agent work
LoopCode keeps a repository's goals, work graph, decisions, and verification evidence available to every coding-agent session.
|
78 % |
Detected social media networks