프롬프트, 평가 및 LLM 옵저버빌리티 시장

프롬프트, 평가 및 LLM 옵저버빌리티 · Show HN에서 출시

189개 제품
제품 및 리서치 지표
제품월간 방문 · 10월작업
MLflow오픈소스Deliver High-Quality AI, Fast148K
Promptfoo오픈소스Ship agents, not vulnerabilities107.8K
YuppThe Yupp Story103.6K
PromptLayerThe collaboration layer for AI engineering teams85.9K
BenchmarkListTrack AI progress with the largest database of benchmarks.65.7K
CoarenaWatch two computer-use agents work on your research .59K
Claude Tuner오픈소스Know when your AI limit hits — and when it's back46.5K
RaindropMCP오픈소스Detect agent issues. Prevent them from happening.42.8K
VerifyWise오픈소스Know every AI system you are running.37.3K
AgnostMCPYour Agents, Self-Improving.30.3K
DrivingBenchMCP오픈소스Can frontier models drive a real car? We give them control of a Toyota Corolla’s steering, accelerator, and brakes29.8K
Neuronpedia오픈소스Explore, visualize, and steer the internals of AI models.28.6K
Oso Cloud오픈소스Visibility and controls to secure agents.28.1K
LocalScore오픈소스LocalScore - Local AI Benchmark21.4K
Big Prompt HubTravel Visual Prompts & Skills20K
PROMPTMETHEUSPrompt Engineering IDE17.1K
ValohaiYour AI product needs a context pipeline, specialized models, and a way to know if it's giving the right answers.12.8K
KastraMCPAuthorization for AI systems.10.6K
ProgramBench오픈소스./ Program Bench10.2K
OpenAPPAMCP오픈소스What is OpenAPPA9.4K
Rival오픈소스Every answer every model gave to the same questions, kept after the models are gone.9.2K
HoneyHiveMCP오픈소스Production AI starts with observability.8.8K
EEBenchElectrical engineering agent benchmark7.4K
Agentmemoryleaderboard오픈소스Measure what your agents remember. Compare what truly matters.7.3K
SpanTurn eng time and tokens into better outcomes7.1K
Tiny AI Arena오픈소스Did you ever click on an “AI Arena” expecting glorious battle and instead get a boring benchmark?6.4K
ScorecardThe simulation platform for agent self-improvement6.3K
Openlit오픈소스Open source Agent Harness Engineering Platform6K
AI BenchySearch AI BENCHY5.5K
SWE-sweep오픈소스SWE- sweep5.4K
OpenPromptCreate. Use. Share.5.3K
KeletDebugging your agent in prod shouldn't require a crystal ball.<5K
APortAuthorize AI agents before they act.<5K
Agentic Control PlaneMCPPermissions, approvals, and cost for the coding agents you run.<5K
OpenPipe오픈소스The OpenPipe platform has migrated to Weights & Biases and CoreWeave. Browse migration details and the OpenPipe technical archive.<5K
LMQL오픈소스Programming language for LLMs.<5K
ComposoMCP오픈소스Teaching machines the human definition of quality.<5K
TrainlyFind the AI failures your monitoring misses.<5K
NoPII오픈소스Sensitive data is reaching your AI. That stops now.<5K
ThisorthisWhich AI is the best?<5K
Opsmeter.ioPrevent LLM bill shock before month-end.<5K
CaberControl what reaches the model.<5K
RAG Doctor오픈소스Deterministic diagnostics for RAG systems<5K
Rampart오픈소스Let agents move fast. Keep the final say.<5K
Tork NetworkOne spine. Twelve nodes. Every decision receipted.<5K
Foglamp오픈소스Know what your agents are doing<5K
FrontierHarness Eval오픈소스Comprehensive harness evaluation<5K
MubitBuild reliable agents with a model for every task.<5K
SeclaiEverything you need around your LLM calls.<5K
Semantic Overlays오픈소스An NX bit for language models<5K
1 / 4 페이지 · 1–50 / 전체 189 개 제품