Official Inference Code of EAGLE-4
- eagle
- gpu
- llm-inference
- sglang
Repository Index
47,133 repositories indexed
217–240 of 340 · Most stars
TranslatedEvoOntology: A Self-Evolving Ontology Layer for Data Agents ⚙️ The EvoOntology plugin builds and evolves an ontology layer for Claude Code/Codex
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
Implementing LLM architectures from scratch in PyTorch
- gemma3
- llama4
- llm
- moe
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.
Pretrained model hub for Keras 3.
Fire your SEO·GEO agency 🔥 A Claude Code skill that audits and optimizes SEO·AEO·GEO·LLMO·NEO(Naver) by itself — 월 50~350만 원짜리 'AI 검색 최적화' 대행, AI 에이전트가 대체합니다
- aeo
- ai-search
- claude-code
- claude-skills
Translated麦麦省钱助手 (Maimai Money-Saving Assistant, "McMc money-saving helper") — an ordering cost optimization Skill based on McDonald's MCP. It works out the cheapest ordering plan for the current store and proactively warns about add-on traps for reaching the order threshold.
SEO foundation checks as an Agent Skill: give it a URL, get a crawler's-eye pass/fail report with evidence. 26 structural checks, zero LLM, deterministic.
TranslatedAI Cross-Border E-commerce Operations Agent Toolkit · Breaks operations SOPs down into 7 reusable AI Agent workflows, including prompts, templates, and real-world cases
Native vLLM serving for Jev decision models
FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.
- accuracy-decline
- ai-safety
- audit-trail
- fact-checking
Fold papers, web pages, files, and AI replies into five levels of detail. Zoom from an overview to the original text.
- arxiv
- llm
- local-first
- open-source
The foundation layer for agentic intelligence.
MCP-NixOS - Model Context Protocol Server for NixOS resources
- ai-assistant
- ai-integration
- ai-tools
- anthropic
A code repository indexing tool to supercharge your LLM experience.
- neovim-plugin
- retrieval-augmented
- embeddings
- rag
Autonomous pentest legion — AI commander + worker swarm + layered fact-intent graph. 3rd Tencent Intelligent Attack-Defense online champion (634 teams · 8h unattended · 1B tokens beat 4.5B). The Nüwa Test: give AIs Create/Language/History, let a civilization grow.
Give satellite imagery, terrain data, buildings, streetview photos to your LLM
- 3d-city-model
- 3d-tiles
- geospatial
- gis
TranslatedA platform for building and running digital employees for enterprises: it solidifies the experience, processes, and judgment standards of professional employees into AI digital employees that can be put to work at any time and are configurable, approvable, and observable.
- ai-agent
- ai-platform
- digital-employee
- enterprise-ai
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
Learning to Recover from LLM Agent Failures at Test Time
Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts
Remory: Learning Residual Memory for Context Compaction
- context-compaction
- inference
- llm-agents
- residual-memory
A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.