PyPI · npm
Arize-ai/phoenix
AI Observability & Evaluation
自定义许可证2026年8月28日 · 指标 2.10.0
全部标签
目录标签
#llm-evaluation
公开记录中带有此标签的全部仓库——标签来自其 GitHub 主题或软件包注册表发布的关键词。健康度量遵循与记录其余部分相同的版本化方法论。
38 条记录
PyPI · npm
mlflow/mlflow
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
Apache-2.02026年9月16日 · 指标 2.10.0
npm · PyPI
comet-ml/opik
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Apache-2.02026年9月16日 · 指标 2.10.0
PyPI
Giskard-AI/giskard-oss
🐢 Open-Source Evaluation & Testing library for LLM Agents
Apache-2.02026年8月28日 · 指标 2.10.0
npm
promptfoo/promptfoo
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
MIT2026年9月16日 · 指标 2.10.0
PyPI · npm
NVIDIA/garak
the LLM vulnerability scanner
Apache-2.02026年10月19日 · 指标 2.10.0
npm · crates.io
langfuse/langfuse
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
自定义许可证2026年9月16日 · 指标 2.10.0
PyPI
Q00/ouroboros
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
MIT2026年9月18日 · 指标 2.10.0
PyPI · npm
NuGuardAI/nuguard
AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.
自定义许可证2026年9月10日 · 指标 2.10.0
PyPI · npm
confident-ai/deepeval
The LLM Evaluation Framework
Apache-2.02026年9月16日 · 指标 2.10.0
Go
praetorian-inc/julius
Simple LLM service identification - translate IP:Port to Ollama, vLLM, LiteLLM, or 60+ other AI services in seconds
Apache-2.02026年9月17日 · 指标 2.10.0
PyPI
truera/trulens
Evaluation and Tracking for LLM Experiments and AI Agents
MIT2026年9月17日 · 指标 2.10.0
PyPI · npm
overmind-core/overmind
The platform for continuously improving AI agents.
AGPL-3.02026年10月19日 · 指标 2.10.0
PyPI · npm
UiPath/coder_eval
Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.
Apache-2.02026年10月19日 · 指标 2.10.0
PyPI
cvs-health/uqlm
[JMLR 2026] "UQLM: A Python Package for Uncertainty Quantification in Large Language Models"
Apache-2.02026年9月19日 · 指标 2.10.0
PyPI
JudgmentLabs/judgeval
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
Apache-2.02026年9月17日 · 指标 2.10.0
npm
microsoft/prompty
Prompty makes it easy to create, manage, debug, and evaluate LLM prompts for your AI applications. Prompty is an asset class and format for LLM prompts designed to enhance observability, understandability, and portability for developers.
MIT2026年9月17日 · 指标 2.10.0
PyPI · npm
Marker-Inc-Korea/AutoRAG
AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.
自定义许可证2026年9月15日 · 指标 2.10.0
Go · Maven · npm
hugalafutro/model-hotel
Multi-Provider AI Gateway - No personal logs by design. Model autodiscovery, Failover groups, High availability, Android companion app, and more - "Because we have LiteLLM at home"
MIT2026年9月10日 · 指标 2.10.0
Hex · npm
ccarvalho-eng/aludel
Phoenix-native LLM evaluation, prompt testing, model comparison, red teaming, and observability for Elixir
Apache-2.02026年9月9日 · 指标 2.10.0
PyPI · npm
alizahidraja/isnad
Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines
Apache-2.02026年10月21日 · 指标 2.10.0
PyPI
b7n0de/proofbundle
Offline cryptographic receipts for AI evaluation results — Ed25519 + RFC 6962 Merkle + optional SD-JWT. Integrity, not truth
MIT2026年9月13日 · 指标 2.10.0
PyPI
Sahil170595/quantfit
Quantize an LLM and check it still refuses what it should — a GPU-aware quantization CLI that measures the safety drift of the quantization it just performed.
Apache-2.02026年10月12日 · 指标 2.10.0
PyPI
scaleapi/agentenv-framework
Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.
Apache-2.02026年10月6日 · 指标 2.10.0
npm
Precisa-Saude/medbench-brasil
Leaderboard reproduzível de LLMs em provas médicas brasileiras (Revalida, INEP) — zero-shot, 3 execuções, análise de contaminação
自定义许可证2026年10月18日 · 指标 2.10.0
npm
huggingface/aisheets
Build, enrich, and transform datasets using AI models with no code
Apache-2.02026年9月19日 · 指标 2.10.0
PyPI · npm
fastaifoundry/fastaiagent-sdk
该仓库未发布描述。
Apache-2.02026年9月10日 · 指标 2.10.0
RubyGems
homemade-software-inc/completion-kit
Your prompts need tests too. Run prompts against real datasets, score outputs with LLM judges, version everything, and compare runs to see what got better.
自定义许可证2026年9月10日 · 指标 2.10.0
PyPI
HarperZ9/flywheel
Flywheel runs AI tasks with a model you choose and keeps a receipt anyone can recheck offline.
自定义许可证2026年10月15日 · 指标 2.10.0
PyPI
phierceweb/pw-core
Python foundation for LLM apps whose prompts and spend you can actually see — versioned prompts, every call recorded and replayable, budgets, evals, jobs.
Apache-2.02026年10月21日 · 指标 2.10.0