Search

AI model: Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1000

AI model: Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1011

Multi-Agent Partially Observable gridworlds in JAX

44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and MCP health monitoring. Your agent teaches itself new behaviors during conversation.

OpenAI adapter for decision learning for AI agent actions with BIGHUB.

The composable agent runtime.

Structured agent memory with semantic queries. Decision intelligence for AI agents — typed reasoning over agent decisions with why, blocked, tensions, alternatives, and whatIf operations.

Skill as agent(s)

Agent-native streaming infrastructure. The streaming runtime built for non-human broadcasters.

OpenClaw Agent Configuration Templates - Lightweight prompt engineering framework for AI agents

TypeScript agent framework for building production-grade, type-safe AI applications — the Pydantic AI way, using Vercel AI SDK.

Governance-first execution framework for multi-agent AI systems.

LLM-powered automatic test generation for Python

A agentic OS that can download and setup and file package , repo from github and run it for you with just one command (AI that has access to your terminal)

KinesisRS is a stateless, JSON-first, multi-chain crypto trading execution layer for LLM Agents.

AI chat and developer platform.

RAG-based internal knowledge copilot for fintech support, providing grounded answers with source citations and safe refusals.

MCTS-guided theorem proving agent — decomposes math problems into a proof tree and explores it with LLMs. Runs on Anthropic/OpenAI APIs or fully offline on Apple Silicon.

Lightweight, git-native multi-agent orchestration framework for autonomous project execution

CLI + daemon for LLM-driven Android UI control — ships with ready-to-use coding agent skills