Live index of the newest LLMOps tooling — track what's shipping in LLM observability and deployment
⭐ Star this repo to bookmark — fresh data every 15 minutes
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.
This 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.
⏰ Last updated: 2026-08-26 05:15 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | anthony-chaudhary/fak | 32 | Go | 2026-08-26 | Create your Agentic AIs. |
| 2 | muhammadwaqasmbd/rag-eval-harness | 1 | Python | 2026-08-26 | Measure RAG retrieval instead of guessing: hit-rate, MRR, recall, nDCG — plus a failure breakdown that tells you whether |
| 3 | calmrocks/ai-engineer-notebooks | 1 | Jupyter Notebook | 2026-08-26 | Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, s |
| 4 | BerriAI/litellm | 57280 | Python | 2026-08-26 | The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tra |
| 5 | kuhlman-labs/fishhawk | 6 | Go | 2026-08-26 | A governed, auditable workflow engine for an agent-driven software factory. |
| 6 | linny006/llmops-radar | 3 | Python | 2026-08-26 | Live index of the newest LLMOps tooling — track what's shipping in LLM observability and deployment |
| 7 | ThakiCloud/thakicloud.github.io | 4 | JavaScript | 2026-08-26 | ThakiCloud Tech Blog |
| 8 | maximhq/bifrost | 7575 | Go | 2026-08-26 | Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ mod |
| 9 | alexejsailer/agentic-nets | 7 | TypeScript | 2026-08-26 | Governed multi-agent runtime for Petri-net workflows, scoped agent permissions, durable state, and replayable execution. |
| 10 | Fast-Editor/Lynkr | 544 | JavaScript | 2026-08-26 | Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude |
| 11 | GetBusbar/busbar | 114 | Rust | 2026-08-26 | Point your existing SDK at one URL and reach every LLM vendor — with real failover, not a try/except. One static Rust bi |
| 12 | muhammadwaqasmbd/llm-gateway | 1 | TypeScript | 2026-08-26 | Provider-agnostic LLM gateway: ordered fallback, hard cost ceilings, per-attempt timeouts, caching and jittered retries. |
| 13 | ngu-gif/genai-role-playbook | 1 | HTML | 2026-08-26 | GenAI Career Roadmap 2026 🚀 | AI Job Paths & Skills Guide |
| 14 | llmspendguard/llm-spendguard | 0 | Python | 2026-08-26 | Know what an LLM job will cost before you run it — and prove your ledger matches the provider's bill. Pre-submit estimat |
| 15 | promptfoo/promptfoo | 24575 | TypeScript | 2026-08-26 | Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, C |
| 16 | garcetemedinamateoandres-sketch/agent-deployment-orchestrator | 1 | HTML | 2026-08-26 | 🚀 AI Agent Deployment on GCP 2026: Fast-Track Production Templates & CI/CD |
| 17 | veritasfuji-japan/veritas_os | 34 | Python | 2026-08-26 | VERITAS OS is an AI agent governance runtime for decision control, policy enforcement, approval workflows, audit trails, |
| 18 | grepture/proxy | 7 | TypeScript | 2026-08-26 | Drop-in proxy for OpenAI, Anthropic, and other LLM APIs. Logging, PII redaction, prompt versioning, and evals out of the |
| 19 | Giskard-AI/giskard-oss | 5772 | Python | 2026-08-26 | 🐢 Open-Source Evaluation & Testing library for LLM Agents |
| 20 | Prime-agentai/agent-approval-gate | 2 | Python | 2026-08-26 | PreToolUse hook for Claude Code: blocks agent spending, account creation and fund moves, queues them for human approval, |
| 21 | Arize-ai/phoenix | 11198 | Python | 2026-08-26 | AI Observability & Evaluation |
| 22 | Theebban/modelpromote | 0 | TypeScript | 2026-08-26 | Governed change control for swapping the AI model in a production application: evaluate, approve, activate with read-bac |
| 23 | Lee2379/multi-agent-ai-analytics-office | 0 | Python | 2026-08-26 | Multi-agent AI analytics office on Hermes and Slack with Supabase data operations, Obsidian/OhMyWiki evidence pipelines, |
| 24 | sophie-nguyenthuthuy/llm-pricing-history | 1 | Python | 2026-08-26 | Daily CI-refreshed history of LLM API pricing — snapshot + append-only change log for ~2,500 chat models (CSV, CC BY 4.0 |
| 25 | haomingkoo/haomingkoo | 0 | — | 2026-08-26 | Applied AI engineer in Singapore building production ML, RAG, agent workflows, evals, vision pipelines, and full-stack A |
| 26 | jochi2018/Soup | 21 | Python | 2026-08-26 | Fine-tune and post-train LLMs with one command—no SSH, no config hell. |
| 27 | Satisfiable-polopony613/EVIE-Preview-4.5B | 0 | Python | 2026-08-26 | Retrieve multilingual visual documents with ultra-compact token embeddings from this Qwen3.5-4B-powered ColPali engine. |
| 28 | coze-dev/coze-loop | 5704 | Go | 2026-08-26 | Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full- |
| 29 | ashrafb8962/agentic-ops-and-rag | 1 | Jupyter Notebook | 2026-08-26 | Build and evaluate production-ready RAG pipelines with hands-on notebooks, templates, and proven performance strategies. |
| 30 | spirex-ds-dev/ai-cockpit-template | 0 | Python | 2026-08-26 | Template for AI-assisted development with Work Item contracts, scope guards, change summaries, and review-ready cockpit |
| 31 | dataelement/bisheng | 11914 | Python | 2026-08-26 | BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive featur |
| 32 | sargentfragrant429/AgentAccessManager | 0 | — | 2026-08-26 | Manage AI model access with a secure gateway featuring load balancing, rate limiting, and audit trails for OpenAI, Groq, |
| 33 | mlflow/mlflow | 27682 | Python | 2026-08-26 | The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, eva |
| 34 | Guruexpl8276/LLM_Inference_Lab | 0 | Python | 2026-08-26 | Measure local LLM inference performance by tracking TTFT, TPOT, and throughput with this research-grade dashboard for Ol |
| 35 | Fauniethermal3522/agentic-dart | 1 | Python | 2026-08-26 | Automate digital forensics and incident response tasks using an autonomous agent aligned with MITRE ATT&CK frameworks. |
| 36 | retardingforcerightbank635/dm-gateway-bot | 0 | Python | 2026-08-26 | Route Telegram DMs through a bot with emoji captcha, verified message relay, and owner reply support to block spam and k |
| 37 | wordenneapolitan768/llm-pricing | 1 | — | 2026-08-26 | Track standardized pricing for 300+ LLM APIs in one JSON file for cost tools, comparisons, and billing dashboards |
| 38 | Orlyoxidized462/py-prompt-versioner | 1 | Python | 2026-08-26 | Version AI prompts in Markdown, inject variables with Jinja2, and manage prompt metadata with strict validation and a CL |
| 39 | Impure-platen433/crabllm | 0 | Rust | 2026-08-26 | Route OpenAI-compatible requests to LLM providers with a fast Rust API gateway |
| 40 | recordrnase224/brix-protocol | 1 | Python | 2026-08-26 | Build runtime reliability guards for LLM pipelines with one wrap() call and configurable protection against common produ |
| 41 | Citrous-districtline59/agent-trace | 0 | Python | 2026-08-26 | Capture and replay every AI agent tool call, prompt, and response to trace sessions and debug complex workflows with ful |
| 42 | ydavidcm9-wq/vigil | 0 | JavaScript | 2026-08-26 | Deliver comprehensive AI-driven security operations with vulnerability scanning, incident response, compliance tracking, |
| 43 | islaagnet27/llm-cost | 1 | C++ | 2026-08-26 | Count tokens and estimate API costs for large language models with a lightweight, single-header C++ library from the llm |
| 44 | cloudrift-ai/emmy | 79 | Python | 2026-08-26 | Optimized GPU compiler for LLM inference. Choose from a list of optimized recipes or optimize your own model via kernel |
| 45 | taishan666/MaxKB4j | 122 | Java | 2026-08-26 | MaxKB4j is an open-source LLMOps platform for LLM workflow applications and RAG developed based on the Java language. Th |
| 46 | GaBySuGy/agent-guardrails | 2 | Shell | 2026-08-26 | 🛡️ Enforce AI rules with Agent Guardrails, preventing breaches and ensuring compliance for your coding agents. Secure yo |
| 47 | pom11/hscc | 4 | Python | 2026-08-26 | Turn a DGX Spark GPU cluster into a self-running team of specialized AI agents — cluster control, role-specialized worke |
| 48 | Farukul-Islam/from-mlops-to-llmops | 0 | PHP | 2026-08-26 | 🔍 Explore the shift from MLOps to LLMOps with materials that simplify AI deployment and enhance document intelligence. |
| 49 | Tearfullnex/SpecGuard | 0 | Python | 2026-08-26 | 🛡️ Enforce AI behavior guidelines with SpecGuard, a tool that turns policies into executable tests for reliable and scal |
| 50 | matiaslanza99/SuperStore.SalesDashboard | 0 | CSS | 2026-08-26 | 📊 Build insightful sales dashboards for SuperStore, enhancing decision-making and driving business growth with real-time |
Every 15 minutes, a GitHub Action runs tracker.py. That script:
- Fetches the latest state from
GitHub Search API. - Diffs against
data/items.json(the previous snapshot). - Rewrites the table above between the
<!-- TRACKER_TABLE_* -->markers. - 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.
See CONTRIBUTING.md — usually you don't need to: the tracker keeps itself current.
If you spot a data-source bug or want to suggest a new column for the table, open
an issue.
If you find this useful, you might also like these other auto-updated trackers from the same maintainer — same mechanism, different upstream:
- trending-claude-skills — What's shipping in Claude Skills this week (
topic:claude-skills) - mcp-servers-live — Live index of newest MCP servers (
topic:mcp-server) - cursor-rules-live — Newest Cursor rules and .cursorrules patterns (
topic:cursor-rules) - claude-code-plugin-tracker — Claude Code plugins and hook configs (
topic:claude-code) - llm-agents-radar — Newest LLM agent frameworks (
topic:llm-agent) - rag-radar — Newest RAG implementations and tools (
topic:rag) - llm-eval-tracker — Newest LLM evaluation tools and benchmarks (
topic:llm-eval) - agent-framework-radar — Newest agent frameworks shipping on GitHub (
topic:agent-framework) - vector-db-live — Newest vector DB projects and integrations (
topic: 60F9 vector-database) - prompt-tools-live — Newest prompt-engineering tools and prompt repos (
topic:prompt-engineering) - agent-eval-harness — Live benchmark of AI coding agents (
topic:llm-eval) - skills-tracker — Tracking new GitHub 'skills' repos (
topic:agent-skills) - awesome-agent-skills — Curated auto-updated awesome-list of AI agent skills (
topic:agent-skills)
MIT — see LICENSE.