Awesome Verified Agents [](https://awesome.re)

August 16, 2026 · View on GitHub

Tools that produce evidence about what an AI agent actually did — not tools that hope it behaves.

An agent that reports its own success is a witness testifying about itself. This list collects the projects that make that testimony checkable: gates that decide before an action runs, records that cannot be quietly edited afterwards, checks that test an output against a source, and benchmarks that put a number on reliability before you ship.

The inclusion bar is one question: what artifact does it leave behind that a human can inspect later? A signed record, a pass/fail, a score, a diff, a trace, a blocked call. Tools that only steer generation — better prompts, better instructions, "be careful" — are out of scope, however useful they are.


Contents


Runtime enforcement

Authorization lives outside the model loop: the model proposes, something else decides.

ProjectEvidence it producesLicenseLast commit
AdrianAnalyzes tool calls and reasoning traces in-flight; runs in audit or block mode, so each decision is a logged allow/denyApache-2.05382026-08-11
invariantGuardrails plus a trace-analysis tool for agent runsApache-2.04452026-01-12
tenuoCapability authorization engine: task-scoped warrants with cryptographic attenuation and offline verification — the warrant itself is the artifactNOASSERTION792026-07-13
agent-browser-shieldBrowser extension, 35+ rules; masks secrets and strips injected instructions before the agent reads the pageNOASSERTION332026-08-15
TealTigerPolicy enforcement and cost tracking with structured audit output (SARIF, JUnit XML, JSON) — machine-readable, so CI can fail on itApache-2.0242026-08-14
SourceryKitHooks the HTTP layer: logs every outbound call and blocks anything off the trusted-endpoint allowlistNOASSERTION182026-08-12
ShaniSigned Authorized Decision Object per decision, with replay prevention and a human-in-the-loop approval pathNOASSERTION02026-06-25

Evidence and attestation

Records designed so that a later reader can tell whether they were tampered with.

ProjectEvidence it producesLicenseLast commit
dos-kernelVerifies an agent's "done" claim against git evidence instead of its self-report; audits commit claims against their own diffsMIT182026-08-13
attestation-envelope-specA spec, not a tool: typed evidence pointers that structurally exclude self-signed assertions, content-hash pinning, ed25519 sigchains, plus a reference verifierMIT02026-08-13
claude-consensusCross-machine agreement protocol (propose / counter / accept / commit) with ACK discipline, so a multi-agent decision has a record independent of any one agentMIT22026-08-14

Output verification

Checking the claim against the source, rather than asking a model whether it looks fine.

ProjectEvidence it producesLicenseLast commit
guardrailsValidators that run over model output and return structured pass/fail per validatorApache-2.072892026-08-14
NeMo GuardrailsProgrammable rails between the app and the model, evaluated per turnNOASSERTION69592026-08-15
verbatim-citation-gateDeterministic first stage: every quoted span must appear verbatim in the retrieved context, so an invented quote fails with no model call; survivors go to a burden-of-proof judge. Known defect: the normalizer is Latin-only, see issue #1MIT32026-08-15
verdict-contractTurns an LLM reviewer's verdict into a process exit status (0 approve / 3 request-changes / 4 contract broken), with the prompt rule and the parser in one file so they cannot drift. Blocking wins from anywhere; approving requires the exact shape. 42 counterexample casesMIT02026-08-10

Evaluation and benchmarks

Putting a number on it before it reaches a user.

ProjectEvidence it producesLicenseLast commit
promptfooDeclarative assertions over prompts, agents and RAG, plus red-team runs — output is a scored matrix you can diff between versionsMIT242722026-08-16
openai/evalsEval framework and a registry of shared benchmarksNOASSERTION191812026-04-14
deepevalMetric suite for LLM and RAG outputs, runnable in a test suiteApache-2.0176162026-08-13
giskard-ossScans an LLM agent for failure classes and produces a report of found issuesApache-2.057532026-08-14
inspect_aiEvaluation framework from the UK AI Security Institute; solvers and scorers are explicit objects, so a result is reproducible from the eval definitionMIT25582026-08-15
AgentLeakBenchmark for privacy leakage in multi-agent systems across 7 channels including tool calls, RAG queries and inter-agent messagesNOASSERTION292026-07-01
ClawBenchFive-layer execution evidence (replay, screenshots, HTTP traffic, browser actions and agent messages) plus interception results and task scores; it does not certify internal reasoning or real-world outcomes beyond the configured evaluatorApache-2.05662026-08-15
Dr. Bench214 expert-curated long-form report tasks with reference bundles and semantic, focus, and retrieval-trustworthiness scores; it does not attest arbitrary agent runsMIT82026-05-02
agent-runtime-integrity-benchDeterministic fault-injection scenarios run against real SDKs, distilled from production incidentsMIT02026-08-14

Observability and tracing

You cannot verify what you cannot see.

ProjectEvidence it producesLicenseLast commit
langfuseTraces, evals and metrics for LLM applications, self-hostableNOASSERTION331812026-08-16
phoenixObservability and evaluation over recorded tracesNOASSERTION110712026-08-16
openllmetryOpenTelemetry-based instrumentation, so agent traces land in the tooling you already runApache-2.073782026-08-10

Self-assessment

Before buying anything: score what you already have.

ProjectEvidence it producesLicenseLast commit
Agent-WizExtracts the agent workflow from LangChain / LangGraph / CrewAI / AutoGen code and runs automated threat modeling over itApache-2.03932025-11-02
agent-leash (LEASH-8)24-statement scored worksheet across 8 control domains, plus the plan-vs-authorize pattern and an approval-design checklist. Docs and templates, no runtimeMIT22026-08-10

How the numbers here work

  • Stars and last-commit dates were read from the GitHub API on 2026-08-16. They are a snapshot, not a live badge, and they will drift. If a row is wrong, that is a bug — open an issue.
  • Last commit is a column on purpose. A list about verification should not hide the staleness of its own entries. Two rows above are more than six months cold; they stay because the work is still worth reading, and you can see the date and decide.
  • NOASSERTION means GitHub could not resolve a standard SPDX identifier from the repo, not that the project is unlicensed. Check the repo before you depend on it.
  • marks a project maintained by the same lab that maintains this list. They follow the same inclusion bar as everything else, and they are the smallest entries here by star count — that is visible in the table rather than hidden.
  • No claim in this list is a benchmark result. Every "evidence it produces" cell describes what the project says it does and what its code and docs show. Where a project's own numbers exist, follow its link — we do not restate performance claims we have not run.

Contributing

See CONTRIBUTING.md. The short version: one project per PR, name the artifact it leaves behind, and say honestly what it does not do. Copyright of your contribution stays yours.


🧩 One piece of a working system

This repository is one piece lifted out of a live operation: one non-technical founder, an AI cofounder, and a fleet of machines that reach consensus with each other and wake the human only for money or the irreversible. It was extracted after it survived production, not written as a demo — and it runs on its own: nothing here phones home to the rest.

See how the whole thing fits together → SYSTEM.md

Its closest neighbours in the in public layer: the-journey · clawrush · dashboards

AI contributors

This project is built by a human + AI team, and the git log says so: Claude writes most of the code, Codex and Grok review it, Gemini feeds the research. Each is credited on a commit only if its output changed that commit's content — no decorative credits. Lab-wide policy, one source for every repo: AI-CONTRIBUTORS.md.