Search

Rakam Systems - Modular AI framework with agents, vectorstore, and LLM gateway

Persistent memory for AI agents. Store, recall, and share knowledge across sessions.

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a 32K context length and optimized through reinforcement learning (RLOO), it provides competitive performance comparable to proprietary models within a smaller parameter footprint. Ideal for low-latency, local, or on-device deployments, Reka Flash 3 is compact, supports efficient qu

See which LLMs you can run on your hardware.

AI-Agent-friendly CLI for ClickZetta Lakehouse

ACP bridge for LangChain Agents

AI Refinery™ by Accenture SDK for developing and executing AI multi-agent solutions.

Multi-agent coding system powered by local LLMs

A JIT Agent Factory that manifests multi-agent teams using Agno, LangGraph, and CrewAI on the fly.

Cognitive Load Manager — real-time metacognitive middleware for LLM agents

Cognitive Load Manager — real-time metacognitive middleware for LLM agents

Self-improving SLM training platform — autonomous fine-tuning with Claude-powered experiment planning

AI-powered image search engine with multimodal embeddings, text-to-image search, LLM captioning, and agentic RAG integration.

Lightweight evaluation metrics for LLMs and AI agents. No platform. No API keys. Just scores.

Command Center for AI Agents - Real-time observability for Claude Code, Codex CLI, and AI coding assistants

Autonomous multi-agent robotics system with DRL-First Hybrid FDIR

AI model: DidulaThavishaPro/ppo-gtc-trading-agent

AI model: mradermacher/SWE-agent-LM-7B-i1-GGUF

AI model: charansoma3001/ithor-agent-lora

AI model: sebastian328/llama-3.3-70b-soap-sleeper-agent-full-finetune-step-1600