|
Lelemon | Open Source LLM Observability & Agent Tracing
Trace prompts, debug tool calls, and track costs in real-time. The lightweight, open-source alternative for OpenAI, Vercel AI SDK, and LangChain. Built in Go...
|
82 % |
|
Logify360 · LLM Observability & Monitoring
LLM observability for OpenAI, Anthropic, Gemini, and 7 more providers. Swap one baseURL to log requests and cost; add the SDK or OTLP to trace agents.
|
81 % |
|
ShieldCore — The AI Security Layer for Enterprise
Intercept, audit, and secure your team and user AI traffic. Real-time DLP, prompt injection protection, and immutable audit trails in under 2ms.
|
80 % |
|
CostImplodeAI - BYOK AI Gateway for Lower LLM Costs
CostImplodeAI is a BYOK AI gateway for routing model requests across provider paths with founder setup, OpenAI-compatible access, and lower eligible routing...
|
80 % |
|
Selixes - Sovereign AI Reliability & Cost Gateway
Sovereign reliability layer for AI-native teams. Automatically failover provider outages, intercept recursive loops, contain concurrent bursts, and enforce c...
|
80 % |
|
OGuardAI: Data protection runtime for AI systems
Data protection runtime for AI systems: model calls, retrieval, agents, logs, stores and exports. Detect, tokenize, and transform sensitive data before it re...
|
80 % |
|
LLM observability & AI agent observability · TripleCloud
TripleCloud is LLM observability for AI pipelines: AI agent observability, online LLM evaluation, LLM monitoring, tracing and AI cost management.
|
79 % |
|
LLMFlow — See what your LLM calls cost
Local LLM observability. One command. No signup. Track costs, tokens, and latency for OpenAI, Anthropic, and more.
|
79 % |
|
LiteLLM — Open-Source AI Gateway & LLM Proxy
LiteLLM is the open-source AI gateway that puts your full AI stack behind one OpenAI-compatible key. Track and cap LLM spend, route to the right model, and s...
|
79 % |
|
Proxle - LLM Observability & Cost Optimization
Stop burning money on LLM development. Cache responses, track costs per feature and user, debug production issues.
|
79 % |
|
Costrace — LLM Cost, Token & Latency Tracking
Open-source observability for LLM APIs. Track cost, token usage, and latency across OpenAI, Anthropic, and Google Gemini in real time — with zero code changes.
|
79 % |
|
ThriftLLM — Self-hosted LLM Proxy with Semantic Caching
One Proxy. Every LLM. Zero Waste. Self-hosted LLM gateway with semantic caching, automatic fallback, cost tracking, and a beautiful dashboard. Drop-in OpenAI...
|
79 % |
|
Orchesis — Open-Source AI Agent Security Proxy | Monitor & Secure LLM API Calls
Open-source AI agent security proxy. 17-phase detection pipeline, loop detection at call #3, 33+ injection patterns. Works with OpenClaw, Paperclip, Claude C...
|
79 % |
|
Kadegate — Kadegate
One OpenAI-compatible endpoint. Access top open models with a single API key.
|
79 % |
|
LLM Gateways — AI Security Layer
Protect your LLM applications from prompt injection, jailbreaks, and data extraction attacks.
|
78 % |
|
ManagePrompt — Local LLM Call Debugger
Capture every LLM API call during development. Full request/response details, token usage, cost estimation, and latency — all in a local web UI.
|
78 % |
|
Lantern
|
78 % |
|
LLM Gateway & Proxy for AI Model Routing | LLMRegistry
LLMRegistry is an LLM gateway and proxy with an OpenAI-compatible API for model routing, failover, semantic caching, spend controls, and observability.
|
78 % |
|
Security Review for Vibe-Coded & AI-Built Apps — SELFOIA
Built your app with Lovable, Bolt, Cursor or Replit? We check it for leaks, break-ins and runaway AI bills. Fixed price. Free check first.
|
78 % |
|
Uplink API - 170+ Open-Source AI Models in One API
Access Llama, Qwen, Mistral, and 170+ open-source AI models through a single OpenAI-compatible API. Intelligent routing, 40% lower costs, deployed globally o...
|
78 % |
Detected social media networks