Helicone/helicone
🧊 Open source LLM-Observability Platform for Developers. One-line integration for monitoring, metrics, evals, agent tracing, prompt management, playground, etc. Supports OpenAI SDK, Vercel AI SDK, Anthropic SDK, LiteLLM, LLamaIndex, LangChain, and more. 🍓 YC W23
Language:TypeScript
Total stars: 2410
Stars trend:
#typescript
#agentmonitoring, #analytics, #evaluation, #gpt, #langchain, #largelanguagemodels, #llamaindex, #llm, #llmcost, #llmevaluation, #llmobservability, #llmops, #monitoring, #opensource, #openai, #playground, #promptengineering, #promptmanagement, #ycombinator
🧊 Open source LLM-Observability Platform for Developers. One-line integration for monitoring, metrics, evals, agent tracing, prompt management, playground, etc. Supports OpenAI SDK, Vercel AI SDK, Anthropic SDK, LiteLLM, LLamaIndex, LangChain, and more. 🍓 YC W23
Language:TypeScript
Total stars: 2410
Stars trend:
20 Dec 2024
9am ▏ +1
10am +0
11am █▍ +11
12pm █▍ +11
1pm █▏ +9
2pm ▉ +7
3pm ▌ +4
4pm █▏ +9
5pm █▏ +9
6pm ▍ +3
7pm ▍ +3
8pm █▏ +9#typescript
#agentmonitoring, #analytics, #evaluation, #gpt, #langchain, #largelanguagemodels, #llamaindex, #llm, #llmcost, #llmevaluation, #llmobservability, #llmops, #monitoring, #opensource, #openai, #playground, #promptengineering, #promptmanagement, #ycombinator
Agenta-AI/agenta
The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.
Language:Python
Total stars: 2418
Stars trend:
#python
#llmasajudge, #llmevaluation, #llmframework, #llmmonitoring, #llmobservability, #llmplatform, #llmplayground, #llmtools, #llmopsplatform, #promptengineering, #promptmanagement, #ragevaluation
The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.
Language:Python
Total stars: 2418
Stars trend:
12 Apr 2025
3pm ▎ +2
4pm +0
5pm +0
6pm █▊ +14
7pm █▋ +13
8pm █ +8
9pm ▋ +5
10pm ▉ +7
11pm ▊ +6
13 Apr 2025
12am █ +8
1am █▏ +9
2am ▍ +3#python
#llmasajudge, #llmevaluation, #llmframework, #llmmonitoring, #llmobservability, #llmplatform, #llmplayground, #llmtools, #llmopsplatform, #promptengineering, #promptmanagement, #ragevaluation
❤1
comet-ml/opik
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Language:Python
Total stars: 6904
Stars trend:
#python
#langchain, #llamaindex, #llm, #llmevaluation, #llmobservability, #llmops, #opensource, #openai, #playground, #promptengineering
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Language:Python
Total stars: 6904
Stars trend:
26 Apr 2025
1am ▎ +2
2am ▍ +3
3am ▍ +3
4am ▏ +1
5am ▏ +1
6am ▍ +3
7am ████▊ +38
8am █▎ +10
9am ▌ +4
10am █▏ +9
11am ▎ +2
12pm ▌ +4#python
#langchain, #llamaindex, #llm, #llmevaluation, #llmobservability, #llmops, #opensource, #openai, #playground, #promptengineering
evilmartians/agent-prism
React components for visualizing traces from AI agents
Language:TypeScript
Total stars: 138
Stars trend:
#typescript
#aiagents, #aimonitoring, #componentlibrary, #developertools, #distributedtracing, #generativeai, #langchain, #llm, #llmobservability, #monitoring, #observability, #opensource, #opentelemetry, #react, #reactcomponents, #tailwindcss, #tracevisualization, #tracing, #typescript, #uicomponents
React components for visualizing traces from AI agents
Language:TypeScript
Total stars: 138
Stars trend:
15 Oct 2025
9pm ▋ +5
10pm ▋ +5
11pm ▍ +3
16 Oct 2025
12am ▌ +4
1am ▍ +3
2am ▏ +1
3am █ +8
4am ▍ +3
5am ▏ +1
6am ▎ +2#typescript
#aiagents, #aimonitoring, #componentlibrary, #developertools, #distributedtracing, #generativeai, #langchain, #llm, #llmobservability, #monitoring, #observability, #opensource, #opentelemetry, #react, #reactcomponents, #tailwindcss, #tracevisualization, #tracing, #typescript, #uicomponents
comet-ml/opik
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Language:Python
Total stars: 15080
Stars trend:
#python
#hacktoberfest, #hacktoberfest2025, #langchain, #llamaindex, #llm, #llmevaluation, #llmobservability, #llmops, #opensource, #openai, #playground, #promptengineering
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Language:Python
Total stars: 15080
Stars trend:
24 Oct 2025
3pm ▏ +1
4pm +0
5pm +0
6pm ▎ +2
7pm +0
8pm +0
9pm +0
10pm █▏ +9
11pm █▍ +11
25 Oct 2025
12am ▉ +7#python
#hacktoberfest, #hacktoberfest2025, #langchain, #llamaindex, #llm, #llmevaluation, #llmobservability, #llmops, #opensource, #openai, #playground, #promptengineering
mnfst/manifest
Smart Model Routing for Personal AI Agents. Cut Costs up to 70% 🦞👧🦚
Language:TypeScript
Total stars: 4576
Stars trend:
#typescript
#cheap, #costtracking, #hermesagent, #llmobservability, #llmrouter, #open, #openclaw, #openclawextension, #openclawplugin, #personalai, #tokentracking
Smart Model Routing for Personal AI Agents. Cut Costs up to 70% 🦞👧🦚
Language:TypeScript
Total stars: 4576
Stars trend:
18 Apr 2026
8pm ▏ +1
9pm +0
10pm +0
11pm ▎ +2
19 Apr 2026
12am ▍ +3
1am ▉ +7
2am █▌ +12
3am █▉ +15#typescript
#cheap, #costtracking, #hermesagent, #llmobservability, #llmrouter, #open, #openclaw, #openclawextension, #openclawplugin, #personalai, #tokentracking
langfuse/langfuse
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Language:TypeScript
Total stars: 25695
Stars trend:
#typescript
#analytics, #autogen, #evaluation, #langchain, #largelanguagemodels, #llamaindex, #llm, #llmevaluation, #llmobservability, #llmops, #monitoring, #observability, #opensource, #openai, #playground, #promptengineering, #promptmanagement, #selfhosted, #ycombinator
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Language:TypeScript
Total stars: 25695
Stars trend:
22 Apr 2026
5pm ▏ +1
6pm ▏ +1
7pm ▏ +1
8pm ▏ +1
9pm +0
10pm ▍ +3
11pm ▉ +7
23 Apr 2026
12am ▎ +2
1am ▋ +5
2am █▏ +9#typescript
#analytics, #autogen, #evaluation, #langchain, #largelanguagemodels, #llamaindex, #llm, #llmevaluation, #llmobservability, #llmops, #monitoring, #observability, #opensource, #openai, #playground, #promptengineering, #promptmanagement, #selfhosted, #ycombinator
FailproofAI/failproofai
Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboard, no account required with a generous free cloud plan
Language:MDX
Total stars: 2529
#mdx
#agentfailure, #agentharness, #agentobservability, #agentreliability, #agenttracing, #aiagent, #claudecode, #codex, #enforcement, #evals, #guardrails, #hermes, #hooks, #llm, #llmfailures, #llmobservability, #npmpackage, #observability, #openclaw, #reliability
Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboard, no account required with a generous free cloud plan
Language:MDX
Total stars: 2529
#mdx
#agentfailure, #agentharness, #agentobservability, #agentreliability, #agenttracing, #aiagent, #claudecode, #codex, #enforcement, #evals, #guardrails, #hermes, #hooks, #llm, #llmfailures, #llmobservability, #npmpackage, #observability, #openclaw, #reliability