91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
Repository Index
142,273 visible repositories in the index
169–192 of 211 · Most stars
The definitive Microsoft 365 Copilot prompt library for business teams. 573 prompts for Office apps, Copilot Studio, security operations, and enterprise deployment.
- ai-prompts
- automation
- awesome-list
- copilot-studio
AI-powered weather intelligence for agricultural commodity futures. Predicts price moves 48-72 hours early across OJ, Coffee, Cocoa, Sugar, Corn and Wheat using Claude Sonnet + satellite data
- agricultural-commodities
- claude-ai
- futures-trading
- machine-learning
tensorflow를 사용하여 텍스트 전처리부터, Topic Models, BERT, GPT, LLM과 같은 최신 모델의 다운스트림 태스크들을 정리한 Deep Learning NLP 저장소입니다.
- tensorflow
- nlp
- natural-language-processing
- question-answering
把你能白嫖的模型额度接进 DSH 同一个池:WorkBuddy 多账号自动容错、十四家扫码登录、76 家免费额度聚合、用量看板、模型路由、本地 OpenAI 网关、积分自动化。
- codebuddy
- dsh-plugin
- failover
- model-provider
LLM (Large Language Model) FineTuning
- gpt-3
- gpt3-turbo
- large-language-models
- llama2
Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard
Mimir — 一站式科研工作台插件:LaTeX 论文边写边编译、arXiv 文献管理、实验追踪、指标图表、GPU 服务器 SSH 任务编排,管理科研全周期。An open-source research workbench plugin for the whole research cycle.
- arxiv
- bibtex
- deepseek
- experiment-tracking
Real-time multimodal desktop agent evolving toward a persistent AI OS interface (0.17 α).
A3C LSTM Atari with Pytorch plus A3G design
- python
- pytorch
- pytorch-a3c
- reinforcement-learning
Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)
- nlp
- reinforcement-learning
- language-model
- nlg
Cool experiments at the intersection of Computer Vision and Sports ⚽🏃
A curated list of artificial intelligence resources (Courses, Tools, App, Open Source Project)
- machine-learning
- deep-learning
- chatbot
- voice-assistant
Business operating system for Claude Code — 57 skills, 21 agents, smart daemon. Unified inbox (WhatsApp/Email/Slack/Telegram), autonomous PR merge, full-AWS monitoring, revenue (Stripe+RevenueCat), e-commerce (Shopify), marketing (Klaviyo/Meta/GA4), voice (Bland/ElevenLabs), APM (Datadog/NewRelic/OTEL), YOLO mode.
- ai-agent
- business-operations
- claude-code
- claude-code-plugin
Case-study journal of MiniMax H3 prompt engineering experiments
DeepSeek-V4.1-Flash-1017 EXL3 on 2x DGX Sparks with TensorFold
Translated🔥🔥🔥Graduation thesis AI assistant, AI graduation thesis, graduation thesis writing, thesis proposal, literature review, AI paper generation, reducing AIGC rate, reducing similarity and plagiarism check rate, formatting and layout, defense PPT
- academic-writing
- ai-paper
- aigc
- chatgpt
AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight models - system prompts, AGENTS.md specs, and Ollama Modelfiles. Built for AI security research and red-team testing.
- ai
- ai-safety
- jailbreak
- jailbreaking
Open-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: shared chat, RAG, skills, a real browser, 4,700+ MCP servers, budgets, approvals and an audit trail. An alternative to ChatGPT Enterprise and Grok Bot. Apache-2.0, built on Pydantic AI.
- agentic-ai
- agents
- pydantic-ai
- python
A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. 🍥
TranslatedGuide to buying and renewing ChatGPT Pro100 (10x, formerly 5x) / Pro200 (20x) in China: Pro100's usage within the Work/Codex plan is doubled with the price unchanged; your own account, Alipay, self-service or manual processing, and a 30-day subscription guarantee. Includes Chinese, English, and Russian.
C++/CUDA single-GPU inference engine for Qwen3.8 (incl. Qwen3.8-Flash-Next with offloaded experts) on the RTX 5090; grew from NInfer
An agentic robotics benchmark for coding agents: 1,156 robot tasks in 35 suites on 47 robots, each answered with a program and verified in a separate sandbox. Runs on Harbor.
- ai-agents
- benchmark
- coding-agents
- embodied-ai
One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.