# Weir

> Weir - unit tests for your agents.

- **Website:** https://github.com/IdoGol24/weir
- **Pricing:** unknown
- **Categories:** Developer Tools, AI Agents
- **Tags:** developer-tools, ai-agents, writing-content
- **Platforms:** Web
- **Last verified:** 2026-09-10
- **Canonical page:** https://linkrena.com/tools/weir

## About

It reads the OpenTelemetry traces your agent already emits and fails the build when sensitive data reaches a sink it should not reach.

Did sensitive data flow through the agent to a sink it should never have reached?

Your agent already answers that question in the traces it emits. Weir reconstructs the session graph, tracks taint through it, and shows the evidence node by node.

Most exports fail this first step, because content capture ships off by default almost everywhere. So weir names the exact switch to flip, read from the instrumentation in your own trace.

Exit 1 , build fails, secret redacted. That finding came from one rule, and a rule is just a file. This is the whole thing:

No code, no DSL. You name a source, a sink, and a mode. The engine builds the graph, tracks the taint, and shows its work.

Rewording your prompts will not move a finding. Adding a step will not move it. If the evidence genuinely weakens, the finding is demoted and says why, instead of quietly flipping to green.

It reads real traces, not ones we wrote. The suite pins a frozen capture that no weir code ever touched ( provenance ). Broken input degrades under one of 18 named rows; it never guesses ( contract ).

Attacker content cannot rewire it. Joins follow evidence tiers, and a finding that crosses a weak one is never verdict-grade.

## Related tools

- [Tako VM](https://linkrena.com/tools/tako-vm): Tako VM is a secure file system and Python execution layer for AI agents: gVisor-isolated Docker containers with job queues, workers, retries, and replay.
- [Ratify Agent Relay Harness](https://linkrena.com/tools/ratify-agent-relay-harness): Offline, one-command reproduction harness + adversarial annex for the Agent Relay x Ratify Phase 2 flagship.
- [Confdiff](https://linkrena.com/tools/confdiff): Semantic, format-aware diff for config & structured-data files (JSON, YAML, TOML, INI, .env, .properties, CSV, XML).
- [Experiential](https://linkrena.com/tools/experiential): An open source model gateway that provides one control plane across closed, open-source, local, and custom models.
- [TDQS](https://linkrena.com/tools/tdqs): An open framework for scoring how well an MCP tool definition communicates to an AI agent.
- [Declick](https://linkrena.com/tools/declick): Compile an API, an MCP server, a database or a web page into a CLI your agent can run.