github.com
Latitude is an open-source observability tool for AI agents. It helps identify failures, dispatch coding agents to fix issues, and verify fixes using real traces. The platform is available on GitHub.
Directory
Search results
Published directory entries matching your search.
github.com
LeanCTX is an open-source context gateway that sits between AI tools and the information they read. It selects task-relevant context, applies supported access and content controls, and records observable context operations and evidence. The engine can run locally through CLI, MCP, hooks and proxy paths, and an SDK embeds supported engine capabilities in applications.
lunary.ai
Lunary is an observability and prompt management platform for LLM-based applications. It provides chatbot analytics, agent tracing, prompt templates, topic classification, PII masking and feedback tracking. A self-hostable option is offered. The Team cloud plan costs $20 per user per month, billed monthly, and payment is required to activate a workspace.
manifest.build
manifest.build is an open source LLM router for AI agents and related tools. It connects AI agents and harnesses to any provider in seconds, supporting subscription, pay-per-token, local model and custom provider options. The tool offers features including model fallbacks, full request logging, autofix for broken provider calls, an LLM gateway for centralized provider management, and observability tools for tracking usage, reliability and costs. The software is open source, allowing users to self-host it or contribute to its development.
mastra.ai
Mastra is a TypeScript AI framework for building agents and AI applications. It includes built-in memory, tool support, MCP compatibility, and observability features to support development from prototype to production. The framework also offers workflow tools, agent factory functionality, cloud deployment servers, and an agent builder for evaluation and iteration.
getmaxim.ai
Bifrost is an open-source AI gateway for LLMs, MCP and agents, offered by Maxim AI. It provides routing, governance, guardrails and observability, and is described as a drop-in replacement for AI SDKs. Enterprise adds features such as SSO, RBAC, adaptive load balancing, cluster mode and in-VPC deployment, free for 14 days.
ncei.noaa.gov
NCEI is a NOAA center that provides environmental data on historical weather, climate, ocean and magnetic field conditions. It maintains an archive of oceanic, atmospheric and geophysical data, archiving over 229 terabytes each month from over 130 observing platforms. NCEI is moving its data and applications to the cloud, which may cause temporary data access delays.
nn-visual.com
NN Visual is an interactive web-based neural network visualizer. It lets users configure hidden layers, select datasets such as auto_mpg, iris, xor, or mnist, and train a network while observing forward and backpropagation step by step. The tool displays training loss, mean absolute error, weight distributions, and node activation brightness. Written explanations accompany the visualizations to teach concepts like gradient descent, weights, biases, and activation functions without requiring code.
open-metadata.org
OpenMetadata is an open-source AI context layer powered by metadata, semantics, and memory that provides a shared, rich understanding of data for people and AI. It was built by the founders of Apache Hadoop, Apache Atlas, and Uber Databook. The unified platform supports data cataloging, discovery, quality, observability, governance, lineage, and collaboration.
parea.ai
Platform and SDK for AI Engineers providing tools for LLM evaluation, observability, and a version-controlled enhanced prompt playground.
portkey.ai
Portkey is a production stack for generative AI builders that offers a suite of tools including an AI gateway, observability features, guardrails and prompt management modules. It is designed to help organizations democratize and productionize generative AI.
promptlayer.com
PromptLayer is a prompt management platform for AI engineering teams. It offers prompt versioning, large language model evaluation tools, and AI agent observability via tracing, logs, and regression sets, plus a visual editor for prompt iteration and collaboration.
github.com
Sacred is a tool developed at IDSIA to help configure, organize, log and reproduce experiments. It provides config scopes, config injection, a command-line interface for changing parameters and running variants, and observers that log experiment information, which can be saved to a MongoDB. Automatic seeding helps control randomness so results remain reproducible.
tensorzero.com
TensorZero builds open-source tools for production-grade LLM applications, including an LLM gateway, observability, optimization, evaluations, and experimentation. The project remains available on GitHub but is no longer maintained. Its website is tensorzero.com.
github.com
Traceloop OpenLLMetry is an open-source observability tool for GenAI and LLM applications, based on OpenTelemetry and maintained by Traceloop. It provides instrumentation for vector databases and frameworks, and includes documentation on getting started and supported destinations.
truefoundry.com
TrueFoundry is an enterprise AI gateway that sits between applications and LLM providers and MCP servers. It offers a unified API for accessing more than 1000 LLMs, along with routing, fallbacks, rate limiting, access control, budgets, guardrails and observability. Deployment options include SaaS, hybrid and self-hosted VPC environments.
vanna.ai
Vanna 2.0 is an AI agent framework that connects large language models to databases. It lets an LLM run SQL queries and generate charts, with tool memory that saves successful interactions to improve later answers. Access controls apply per user, and optional hosted admin features include observability, agent memory, file storage, audit logs and data retention. It works with various LLM providers and databases.
weco.ai
Weco is a research and product lab building recursively self-improving AI. Its platform points at an eval script and iteratively optimizes code against a metric the user defines, such as speed, accuracy or cost. Supported model providers include GPT, Claude, Gemini, Kimi, GLM and MiniMax, with bring your own key.