llmops-radar

LLMOps Radar is a continuously updated tracker that discovers, catalogs, and scores new LLMOps tools as they appear on GitHub and Product Hunt. Unlike static awesome-lists, it runs daily via GitHub Actions to surface tools launched in the past week across categories like observability, prompt management, cost tracking, and gateways. The list is auto-updated every 15 minutes by a GitHub Actions cron. Each commit reflects a real change in the upstream data source — new items added, expired items removed — so you can rely on what you see being current. ## How it works Every 15 minutes, a GitHub Action runs `tracker.py`. That script: 1. Fetches the latest state from `GitHub Search API`. 2. Diffs against `data/items.json` (the previous snapshot). 3. Rewrites the table above between the `<!-- TRACKER_TABLE_* -->` markers. 4. Commits `feat: +N added, -M removed (timestamp)` if anything changed. No external services. No paid APIs. Just a public data source and a free GitHub Action. ## Current Items The repository includes a table of 50 tracked items, with columns for name, stars, language, last update, and description. Examples include: - **ChainForge** – visual programming environment for testing prompts - **MLflow** – AI engineering platform for agents, LLMs, and ML models - **LiteLLM** – AI gateway with cost tracking - **Phoenix** – AI observability and evaluation - **promptfoo** – testing and red teaming for prompts, agents, and RAGs - **Composio** – toolkits and sandboxed workbench for AI agents - **Opik** – debugging, evaluating, and monitoring LLM applications ## Related trackers The maintainer also offers other auto-updated trackers for related topics, such as: - trending-claude-skills - mcp-servers-live - cursor-rules-live - llm-agents-radar - rag-radar - llm-eval-tracker - agent-framework-radar - vector-db-live - prompt-tools-live - agent-eval-harness - skills-tracker - awesome-agent-skills ## License MIT – see `LICENSE`.