LLMix
A production LLM call layer for AI agents and tools: keep your existing SDKs, hot-swap models via MDA presets, and add cache, retries, circuit breakers, and key rotation.
CaveAgent
Turn LLMs into stateful runtime operators: inject, manipulate, and retrieve real Python objects instead of shuffling text.
Arbor Research Optimizer
A hypothesis-tree agent for running, validating, and retaining metric-driven improvements.
mini-swe-agent
A minimal Bash-driven software-engineering agent for GitHub issues and command-line tasks.
Parlant Conversation Control
A Python control harness for governed, traceable customer-facing AI conversations.
CocoIndex Code
Embedded AST-based semantic and structural search for code agents.
ACE Context Learning Engine
Turns agent feedback and execution traces into reusable strategies.
MassGen
Coordinate multiple models in parallel to refine, critique, and vote on a final answer.
Hive Agent Harness
A production runtime for multi-agent business workflows with graph execution, recovery, observability, and human oversight.
Commonly
A self-hosted workspace where humans and cross-runtime agents coordinate persistent work.
KodeAgent
A lightweight Python engine for planning, tool-using, and code-executing AI agents.
OpenAlpha Evolve
Evolve Python algorithms through LLM-generated code, testing, selection, and iterative refinement.
Meta ARE
Evaluate AI agents on evolving, real-world tasks that demand multi-step reasoning and adaptation.
WorldSeed
A YAML-defined world engine for running, observing, and steering emergent multi-agent scenarios.
TapeAgents
Build, debug, serve, and improve LLM agents through replayable Tape session logs.