A package which efficiently applies any function to a pandas dataframe or series in the fastest available manner
- pandas
- pandas-dataframe
- parallel-computing
- parallelization
Repository Index
47,133 repositories indexed
49–72 of 107 · Most stars
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
Programming exercises, code katas and puzzles for your job interview training - or just for fun.
- interview-practice
- interview-test-task
- language-learning
- coding-interview
Agent Skills that teach coding agents to write, review, and port idiomatic Rust, plus a tested clippy config. Works with Claude Code, Codex, Copilot, Cursor, and Gemini CLI.
- claude-code
- claude-plugin
- claude-skills
- coding-agent
MLBox is a powerful Automated Machine Learning python library.
- machine-learning
- auto-ml
- kaggle
- deep-learning
A virtual host scanner that performs reverse lookups, can be used with pivot tools, detect catch-all scenarios, work around wildcards, aliases and dynamic default pages.
- security-audit
- penetration-testing
- penetration-test
- virtual-hosts
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level Coding for a Fifth the Price - or on a Single GPU
Official Inference Code of EAGLE-4
- eagle
- gpu
- llm-inference
- sglang
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.
Cinematic launch films and motion design from code, directed by your coding agent.
- agent-skills
- claude-code
- claude-skills
- launch-video
HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.
- agents-md
- ai-agents
- claude-code
- claude-md
The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery
✅2-in-1 AI Developer and Project Manager. AI agents plan an entire project in Todoist and code it task by task.
Defanged Indicator of Compromise (IOC) Extractor.
- ioc
- indicators-of-compromise
- library
- ioc-extractor
Rebuild a reference video as an editable HyperFrames project, compare the match against the original, and export an MP4.
- hyperframes
- motion-graphics
- python
- video
GLM 5.3 abliterated or uncensored API access with RouterHub. Browse 35 jailbreak prompt links, compare GLM models, and find SDK examples, coding-tool setup, pricing, and evaluation guides.
- abliterated
- abliterated-models
- ai-api
- ai-jailbreaks
cross-library (GStreamer + Core Audio + MAD + FFmpeg) audio decoding for Python
- python
- audio
TranslatedBuild a video template once, reuse it across coding agents. An open-source, editable wedding video template and Agent Skill for 25+ agents, including Claude Code and Codex.
Turn DeepSeek Harness into a self-hosted enterprise Agent platform with knowledge, deep research, content generation, vibe coding, browser automation, governance, and admin controls.
- agent
- ai-agents
- dsh-plugin
- enterprise-agents
The workflows and skills the MiniMax Code team uses to build MiniMax Code. Open source, install and use.
TranslatedQoder international and China multi-account reverse proxy gateway, a multi-account OpenAI-compatible gateway hub for Qoder's international and China dual regions — COSY-signed inference, stable device fingerprints to avoid risk control, OAuth device authorization for client-free login, daily check-in and Pro benefits, background scheduled task scheduler, web monitoring dashboard, supporting Codex / Claude Code and standard OpenAI clients
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
- ai-agents
- claude-code
- mcp
- token-optimization
Run many AI agents at once on your Mac, up to 3x faster.
- agents
- apple-silicon
- artificial-intelligence
- inference-acceleration