A Python package to assess and improve fairness of machine learning models.
Open source
24 alternativesRhesis
Rhesis helps AI teams annotate and review agent behavior so engineers can improve their agents.
About Rhesis
Rhesis lets AI teams collect structured feedback on agent behavior and use it to improve the agent. Teams connect an agent, share a link with reviewers, gather pass/fail verdicts and comments, and turn recurring feedback into tests and metrics that run on later changes.
It includes a browser playground for chatting with the live agent and creating test sets, test generation from requirements, files and connected tools, conversation simulation and evaluators, and access to feedback through the SDK, REST API and MCP clients. Agents connect through a public REST endpoint or an outbound WebSocket SDK connector, and the product is described as available as SaaS or self-hosted.
Key features
- Connect agents via public REST URL or outbound WebSocket SDK connector
- Browser-based playground to chat with live agent and create tests
- Structured pass/fail verdicts and comments per turn or metric
- Generate tests from PRD, uploaded files, Notion, Jira, Confluence
- Simulate conversations and run 60+ DeepEval, garak, custom metrics
- Access feedback via SDK, REST API, and MCP clients
Best for: AI engineers, domain experts, and product managers who jointly review and improve AI agents.
Good for
- Reviews stay linked to the test case and agent version that produced them
- Reviewers use browser UI with no code while builders use SDK and MCP on same data
- Agent can run in private VPC or laptop without public URL via outbound WebSocket
Rhesis at a glance
- Website
- github.com/rhesis-ai/rhesis
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Rhesis alternatives
Tools and sites you could use instead, ranked by how closely they match.
This TabGAN repository reviews research on applying GANs to generate tabular data.
Open source
24 alternatives
Captum explains model behavior and supports interpretability analysis for PyTorch systems.
Open source
24 alternatives
The Featuretools Python library supports automated feature engineering and is published as open source.
Open source
24 alternatives
Feature Engine provides Python tools for feature engineering and selection that are compatible with scikit-learn.
Open source
24 alternatives
Giskard provides open source evaluation and testing tools for LLM agents.
Open source
24 alternativesPopular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
Rhesis FAQ
How do I connect my agent to Rhesis?
If it serves a public REST endpoint, paste the URL. Otherwise use the SDK connector, which opens an outbound WebSocket so the agent can run from a laptop or VPC with no public URL.
How do reviewers leave feedback?
In the playground they chat with the live agent, create and run test sets, simulate multi-turn conversations, and leave pass/fail verdicts and comments down to the individual metric or conversation turn.
How do builders use the feedback?
Read it from the SDK or REST API, or work with it from Cursor, Claude Code and other MCP clients through the Rhesis skill, then fix the agent and run the same tests again.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.