Loading...
Loading...
LiteLLM: Call every LLM API like it's OpenAI [100+ LLMs]. It is listed under Development & Code on AI Registry with a free plan and paid upgrades.
The tools below are approved listings in the same category, ordered by how closely their tags match LiteLLM. This is an automatic list. We have not written a researched verdict for LiteLLM yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
Context layer for production-grade AI agents
Airbyte is an open source data movement platform that replicates data from more than 700 source systems into warehouses, lakes, vector databases and AI agents. It runs ELT pipelines to the storage layer of your choice and adds two layers aimed at AI: a Context Store that provides entity resolution and semantic search o...
The programming language for AI
Boundary is the company behind BAML, a programming language designed for writing AI agents and the code they produce. The name stands for Basically a Made up Language. It reads like TypeScript, with unions, generics, lambdas and pattern matching, but removes the escape hatches an agent could hide behind: there is no an...
Building infrastructure tools to help large companies customize their…
Chima is a San Francisco company that builds and deploys generative AI agents for large enterprises. Its platform, described as a Compound Human Reasoning system, runs agents that take over workflows across operations, marketing, customer support, sales, compliance and security. Rather than a self serve tool, it is del...
The web data API for searching and scraping. 🔥
Firecrawl is a web data API that turns live pages into clean Markdown and structured data for AI agents and applications. Four core operations cover most work: search the web and return the full content behind each result, scrape a single page into Markdown, JSON or a screenshot, map a site to discover its URLs, and cr...
Reimagining how Machines Learn
Lucidic AI builds custom language models and agent harnesses trained on a customer's own data. Its approach is to train the model and the surrounding harness together, covering elements such as system prompts, tool descriptions, guardrails, policies, context and memory, rather than tuning model weights alone or optimiz...
Fix your AI agent's errors at runtime, so they never happen twice
Your agent worked fine yesterday. Today it loops, drops context, or calls a tool with the wrong arguments, and you find out from a user. Teams shipping AI agents change prompts, models, and tools constantly, and the same failures keep coming back in production: context loss, loops, broken tool calls, regressions after ...