Reach more potential users and drive product growth and revenue.
AdvertiseTools tagged with "Evaluation"
Warp
Free ListingStars: 65.2KOpen infrastructure for cloud software factories
Warp is an agentic development environment, born out of the terminal, offering open infrastructure to build, measure, and interact with agents across the SDLC so teams ship more and spend less.
nanochat
Free ListingStars: 60.1KMinimal experimental harness for training LLMs
nanochat is a minimal, hackable harness for training LLMs end to end on a single GPU node, covering tokenization, pretraining, finetuning, evaluation, and inference. It is pitched as the best ChatGPT that $100 can buy.
Langfuse
Free ListingStars: 35.1KOpen Source Agent Evals & Observability
Open source platform for tracing, evaluating, and improving AI agents. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.
Laya
Free ListingStars: 34KTyped decisions with calibrated probabilities in one pass
Laya is a non-autoregressive System 1 decision engine for typed choice, score, and yes/no questions over text. It returns calibrated probabilities in one forward pass across 100+ languages and routes requests to the right checkpoint.
Mastra
Free ListingStars: 28.9KTypeScript framework for AI agents and applications
Mastra is an open-source TypeScript framework for building AI-powered applications and agents, with agents, workflows, memory, workspaces, and observability for moving from prototype to production.
promptfoo
Free ListingStars: 26.1KAutomated testing and red teaming for LLM apps
Promptfoo is an open source CLI and library for evaluating and red-teaming LLM-based applications. It provides automated testing to find and fix AI risk, compare model providers, and test prompts, agents, and RAGs during development.
Agent Development Kit (ADK)
Free ListingStars: 22KOpen-source framework for building production AI agents
ADK is an open-source, code-first framework for building, evaluating, debugging, and deploying reliable AI agents at enterprise scale. It is available in Python, TypeScript, Go, Java, and Kotlin.
Arize Phoenix
Free ListingStars: 11.6KAI Observability and Evaluation
Arize Phoenix is an open-source AI observability platform for tracing, evaluating, and improving LLM applications. It provides tracing via OpenTelemetry, LLM-based evaluations, prompt management, and experiments to compare changes. Built
Kev
Free ListingStars: 9.6KSmall Jev-like decision models to train and run yourself.
Kev is a family of small decision models built on Qwen3.5 and Qwen3.8, based on Jev's architecture. Use pretrained weights or train your own, with yes/no, multiple-choice, and rating questions in one request.
Harbor
Free ListingStars: 5.6KEvaluate and optimize sandboxed agents and models.
Harbor is a framework from the creators of Terminal-Bench for evaluating and optimizing agents and language models in container environments. It supports arbitrary agents, custom benchmarks, parallel cloud experiments, and rollouts for RL
ADR
Free ListingStars: 2.1KEnterprise security for AI agents
ADR (Agentic AI Detection and Response) is an enterprise security system for AI agents. It discovers unsanctioned AI tools, observes agent activity, benchmarks defenses, and detects threats across employee-facing and customer-facing agents.
Folkbench
Free ListingStars: 2KAI relay station benchmarks and rankings
Folkbench benchmarks AI API relay stations and publishes availability, response time, and pricing rankings, plus Folkbench Switch, an open-source desktop client for Claude Code, Codex, and similar tools.
Overmind
Free ListingStars: 0.7KThe training platform for specialized agents
Overmind is a training platform for specialized AI agents that turns production traces into datasets, evaluations, fine-tuned models, and deployments you own, with hosted or self-hosted operation.

