BAML is a programming language for agents built to replace other toolchains that were designed for humans. It emphasizes incremental adoption, strong typing, and tooling that supports agent-focused development. The language aims to read like TypeScript while enforcing stricter safety and observability guarantees. It targets developers who build AI-assisted code and workflows, offering integration options with existing languages and runtimes.
BAML runs standalone on multiple operating systems and can be embedded inside existing projects in many languages. It provides an agent-first toolchain and a compiler designed to be fast and capable of tracing and profiling code across distributed components. The project emphasizes bridging to other languages so that type information and orchestration can cross the language boundary.
Key aspects include an emphasis on observability and tracing, an AI function model that treats model calls as typed functions, and a workflow system with concurrency controls. The aim is to reduce slop in code and improve reliability when writing agent-oriented software.
The project pages describe plans to offer cloud tools later and emphasize openness under an Apache-2 license. They discuss platform support, bridging targets, and how users can adopt BAML within existing codebases, with ongoing work around tooling, runtimes, and observability layers.
Adaptive Engine evaluates, tunes, and serves LLMs for enterprise AI, using reinforcement learning to optimize models and production feedback.
Prompt Octopus compares model responses side-by-side, with a VSCode extension and API key options for use in your codebase.
Antigma provides self-contained, self-organizing agents for developers, with Ante as an autonomous coding agent that runs locally or cloud-backed, in a terminal and via various interfaces.
Lingo.dev is a localization engineering platform for product teams to measure translation quality, choose translation providers, and manage localization…
Zipy provides AI-powered session replays, error tracking, performance monitoring, and product analytics for developers and product teams.
Miko is a self-hosted AI coding agent that connects Slack, Linear, GitHub, and GitLab to coding agents, enabling task assignment and pull-request reviews.