Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
Repository Index
80,339 visible repositories in the index
25–48 of 55 · Most stars
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
- large-language-models
- prompt-optimization
- compound-systems
- textual-gradients
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
- claude-code
- token-optimization
- context-window
- token-usage
Reference implementation for DPO (Direct Preference Optimization)
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.
Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
- natural-language-processing
- prompt-tuning
- pretrained-language-model
- p-tuning
Run LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
- ai-agent-tools
- context-compression
- context-pruning
- context-window-optimization
Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.
- ai-agents
- ai-companion
- digital-human
- digital-life
An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
- agents
- calibration
- classification
- decision-making
Optimized Agentic and LLM Bulk Processing Over Your Data
A crowdsourced distributed cluster for AI art and text generation
- ai
- distributed-computing
- flask-api
- gpt
Building blocks for rapid development of GenAI applications
- rag
- document-search
- evaluation
- guardrails
Aion 2 AI Prompt Engineering Toolkit - Standalone Desktop Trainer Setup
- aion-2
- aion-2-2026
- aion-2-game
- aion-2-optimizer
Local inference engine optimized for NVIDIA Blackwell
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
- apple-silicon
- clover
- coding-agents
- decision-models
Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.
- ai-gateway
- claude-code
- codex
- coding-agent
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
- deep-learning
- llm-agents
- optimizer
- pytorch
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
- meta-learning
- reinforcement-learning
- rsi
- ai-agents
TranslatedPrompt editor for DSH with method cards, draft comparison and quote recovery. DeepSeek Harness (DSH) prompt engineering plugin. Spot omissions in the input box and add a sentence picked from 90 method cards, or rewrite against the original draft, check quotes and restore the original words.