Results for “observability for LLM apps”
Closest first
A context management interface
Tree-sitter AST blueprints instead of raw code for LLMs
open-source Datadog Alternative
an API for using LLMs on your own data
After struggling with complex prompt engineering and unreliable parsing, we built L1M, a simple API that lets you extract structured data from unstructured text and images.
Persistent memory for LLMs and apps. Content-addressed storage with dedupe, compression, full-text and vector search.
Command-line interface for the Arcane Engine
Fast, language agnostic, software testing using LLM agents
The LLM Evaluation Framework
Dev-Friendly OpenTelemetry Observability with Open Standards
build a realtime LLM app in 30 lines, with no vector database
open-source API Proxy for reliability and observability
Build and embed open-source AI copilots into your product
an OSS standard for LLM-based code review
Vectara is a "batteries included" retrieval augmented generation platform.
an open source LLM evaluation framework
open-source LLM chat management and tool call framework
a programming language designed to be difficult for LLMs
Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track costs, debug prompts, and monitor context window usage across your AI development sessions.
a muscle memory cache for LLMs
Quickly iterate when fine-tuning open-source LLMs
and seeing all the bad things people did.
A multi-source LLM benchmark across text, image, and audio that measures JSON value accuracy per field, not just schema compliance. 7 metrics, full leaderboard.
the first full-stack framework powered by an LLM
Claude, local/self-hosted)
eBPF observability for AI agents, no code changes
I finally believe it's ready for its first release.