Data / Repositories / Evals
Evals repositories on GitHub: 9 ranked by stars
9 public repositories tagged Evals are on GitHub, with 51,372 stars between them; 8 had a push in the last 30 days. Most are written in TypeScript (4), Python (4). The most starred: mastra-ai/mastra (28,817), Arize-ai/phoenix (11,834), pydantic/logfire (4,512).
SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.
Every repository, most starred first
| Repository | What it is | Language | Stars | Forks | License | Last push | Read |
|---|---|---|---|---|---|---|---|
| mastra-ai/mastra | Mastra is the modern TypeScript framework for AI-powered applications and agents. | TypeScript | 28,817 | 2,981 | Oct 14 | Oct 14 | |
| Arize-ai/phoenix | AI Observability & Evaluation | Python | 11,834 | 1,203 | Oct 14 | Oct 14 | |
| pydantic/logfire | AI observability platform for production LLM and agent systems. | Python | 4,512 | 313 | MIT | Oct 10 | Oct 11 |
| ombharatiya/ai-system-design-guide | AI system design guide for engineers building production AI systems and evals. | 3,577 | 735 | MIT | Oct 8 | Oct 14 | |
| MCPJam/inspector | Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps. | TypeScript | 2,258 | 295 | Oct 14 | Oct 14 | |
| mclenhard/mcp-evals | A Node.js package and GitHub Action for evaluating MCP (Model Context Protocol) tool implementations using LLM-based scoring. This helps ensure your MCP server's tools are working… | TypeScript | 134 | 13 | MIT | Jun 23, 2025 | Oct 14 |
| openlayer-ai/jevals | Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya. | Python | 105 | 11 | MIT | Oct 15 | Oct 15 |
| neatlogs/neatroots | neatroots: see, check and replay your AI agent's runs on your machine while you build it. Local-first, by Neatlogs. | TypeScript | 81 | 55 | Apache-2.0 | Oct 21 | Oct 21 |
| PrefectHQ/prefect-mcp-server | Prefect MCP server | Python | 54 | 40 | MIT | Oct 1 | Oct 14 |
By language
- TypeScript 4
- Python 4
Related topics
- LLM 5
- MCP 5
- Agents 4
- AI 4
- OpenAI 3
- Anthropic 2
- LLM evaluation 2
- Observability 2
- MCP server 2
- JavaScript 1
- Nextjs 1
- Node.js 1
Read from GitHub by SpecStream between October 11, 2026 and October 21, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.