Cadenya
Cadenya is an agent runtime built around a layered model: tools connect once through MCP, OpenAPI specs, or existing endpoints; agents…
Developer libraries for building agents (LangChain, CrewAI, LangGraph, AutoGen).
Cadenya is an agent runtime built around a layered model: tools connect once through MCP, OpenAPI specs, or existing endpoints; agents…
Reflexio sits between your agent and your logs, pulling corrections, failed paths, and successful outcomes into a learning loop that…
Paritok sits between your agent and Anthropic (or any OpenAI-compatible upstream) via one environment variable change. It runs three…
The core workflow is a CLI loop — init, develop, eval, push — built on top of the open-source Verifiers library, with access to 2,500+…
Keystroke gives teams a single platform to build agents with persistent memory, a filesystem, and code execution alongside multi-step…
Authoryze issues virtual cards for each agent, enforces per-transaction and aggregate spending caps server-side, and routes anything above…
EverMemOS, built by EverMind, is a memory infrastructure layer that gives AI agents persistent, inspectable, and portable memory across…
The protocol is deliberately minimal: one markdown file on disk, four rules, no server. Two agents take alternating turns editing a single…
The platform generates a typed Ruby class per agent, living under app/agents/ in your existing Rails repo. Knowledge agents answer…