LLM for Drug Editing, ICLR 2024
- chatgpt
- conversation
- drug
- drug-discovery
Repository Index
65,264 visible repositories in the index
793–816 of 875 · Most stars
Continuity for the agent itself. An MCP server that gives an AI agent a memory of its own, written in its own words and kept on your machine, so it wakes as itself every session.
LLM-powered Text-to-SQL evaluation toolkit: schema ingestion, retrieval eval, and standalone SQL judge/re-scorer.
TranslatedKnowledge ingestion for public web pages and WeChat Official Account articles: distills core knowledge, generates Obsidian notes by topic, and maintains an index and logs; a single article is driven by an Agent, and batch distribution uses CC Connect.
- cc-connect
- claude-code
- knowledge-management
- obsidian
A dual-agent framework leveraging left-brain logic (structured coding, syntax validation, debugging) and right-brain intuition (macro architecture, creative patterns, UX flows). It splits cognitive loads to boost LLM development efficiency, preventing hallucination while maximizing system scalability.
DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.
- benchmark
- calibration
- decision-making
- evaluation
Parse NTLM challenge messages over HTTP and SMB
- reconnaissance
- information-gathering
- ntlm-authentication-protocol
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
- agent-framework
- agentic-workflow
- aiforscience
- llm-agents
A collection of tools for painting super-resolution images
- microscopy
- super-resolution
- smlm
- dna-paint
Open-source agentic security operations platform:
- agentic-security
- cyber-security
- cyber-threat-intelligence
- cybersecurity
TranslatedSay "¥35, not spicy, no ice" → one answer + a copyable order card. Official calculate-price only. Zero-dependency MCP skill. McDonald's ordering Skill.
TranslatedBatch ingestion of Douyin authors' works: identifies the author and fetches public works page by page, generates Obsidian notes by topic, and maintains the author directory, index, and logs; driven by an Agent, with CC Connect as an optional integration.
- agent-skills
- batch-processing
- douyin
- knowledge-management
Auto-updated tech internships in India from 160+ company career pages, with Telegram alerts. Serverless on GitHub Actions.
- github-actions
- india
- internships
- job-board
End-to-end DevOps TaskFlow API — FastAPI, PostgreSQL, SQLAlchemy, Alembic, Docker Compose, Pytest and GitHub Actions CI,Kubernetes,prometheus,Grafana,helm,k9s,kompose,minikube,helmify
- alembic
- docker
- docker-compose
- fastapi
BIA Bob is a Jupyter+LLM-based assistant for interacting with image data and for working on Bio-image Analysis tasks.
An LLM running on an NPU inside an LLM. Karpathy's stories260K writing stories on a vector unit compiled into Qwen3.5-4B's weights.
Translated🍟 McD Saver (麦麦省钱助手, "McDonald's money-saving assistant") — a money-saving ordering Agent Skill built on McDonald's China's official MCP: real-time price verification via the official calculate-price, coupon combination optimization, sunk-cost check-up and multi-order coupon scheduling, and final prices calculated on the same basis across four channels: official coupons, set meals, group-buy vouchers, and points. Online price estimation without login.
- agent-skill
- mcdonalds
- mcp
- python
JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.
- agent-skills
- calibration
- claude-code
- decision-model
A 36s cinematic short film made by Claude Code (Opus 5.5) driving Blender 5.2 headless from Python
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
- ai-routing
- anthropic
- claude
- claude-code
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.
TranslatedMcDonald's meal pairing decision Skill | Computes the top three optimal choices out of 1881 combinations, and tells you why they are not the others. Calorie control, dietary restrictions, and max-min fair allocation for group orders; the LLM does not take part in calculating money, and every number is traceable.
Autonomous DFIR agent: point it at disk images, memory dumps or log exports and get back an investigation that shows its work. Volatility 3, Plaso, YARA and any OpenAI-compatible LLM.
Describe a thing, get a hologram, a 3D model and its parts: built by any AI agent, honestly.
- 3d-visualization
- agent-skills
- ai-agents
- claude-code