29 projects
managed-research
SDK, MCP, and schemas for authenticated Managed Research.
neural-inquisitor
neural-inquisitor
synth-optimizers
Public Synth MIPROv2 optimizer package.
synth-containers
Shared Synth container and environment runtime substrate
dungeongrid
DungeonGrid: text-first cooperative dungeon-crawl environment for multi-agent benchmarks
synth-ai
Python-only SDK for Synth containers, tunnels, and container pools
synth-managed-research
Public SDK, MCP, and schemas for Managed Research.
voyager-ai
Prompt optimization and continual learning for AI agents
tanha
Tanha — platform SDK for building autonomous agent systems.
agent-pubsub
Pub/sub messaging infrastructure for AI agent systems.
long-horizon
Long-horizon planning and execution for autonomous agents.
agent-harnesses
Harness infrastructure for running and evaluating AI agents.
long-horizon-agent
Long-horizon autonomous agent framework.
lm-tasks
Task definitions and runners for language model evaluation.
agent-tasks
Task environments and evaluation harnesses for AI agents.
mipro-v2
Multi-prompt Instruction Proposal Optimizer — automated prompt optimization
mipro-ai
Multi-prompt Instruction Proposal Optimizer — automated prompt optimization
recursive-lm
Recursive Language Models
rlm-ai
Recursive Language Models for AI
oneshot-synth
Add your description here
horizons-ai
Horizons AI - Advanced Reinforcement Learning Environments
synth-env
None
synth-sdk
SDK for Synth
synth-graph
Modern graph orchestration library for building stateful, multi-actor applications with LLMs
finetuning
Modern fine-tuning library for LLMs with LoRA, QLoRA, and full fine-tuning support
craftaxlm
Add your description here
zyk
Simple LM api wrappers for production
smallbench
Small Benchmarks for LM Agents
apropos-ai
Learning algorithms for production language model programs
