chemany/Mente

Mente is a unified AI agent for coding, automation, gateway workflows, and long-term memory.

This repository also configures its own agents. See what Mente tells them →

11Stars on the repository
165Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

pytorch-fsdp

49

chemany/Mente

Skill Claude CodeCodex

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2.

not rated 11 3mo ago B 37 tokens copy · 100% MIT

pytorch-lightning

50

chemany/Mente

Skill Claude CodeCodex

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

not rated 11 3mo ago A 59 tokens copy · 83% MIT

chemany/Mente

Skill Claude CodeCodex

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

not rated 11 3mo ago A 46 tokens copy · 86% MIT

chemany/Mente

Skill Claude CodeCodex

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

not rated 11 3mo ago A 58 tokens copy · 94% MIT

simpo-training

53

chemany/Mente

Skill Claude CodeCodex needs its repo

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

not rated 11 3mo ago A 62 tokens copy · 80% MIT

slime-rl-training

54

chemany/Mente

Skill Claude CodeCodex

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

not rated 11 3mo ago A 52 tokens copy · 94% MIT

chemany/Mente

Skill Claude CodeCodex

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

not rated 11 3mo ago A 50 tokens copy · 91% MIT

tensorrt-llm

56

chemany/Mente

Skill Claude CodeCodex

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

not rated 11 3mo ago A 75 tokens copy · 86% MIT

chemany/Mente

Skill Claude CodeCodex needs its repo

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

not rated 11 3mo ago A 83 tokens copy · 97% MIT

whisper

58

chemany/Mente

Skill Claude CodeCodex

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…

not rated 11 3mo ago B 67 tokens copy · 91% MIT

canvas

59

chemany/Mente

Skill Claude CodeCodex

Canvas LMS integration — fetch enrolled courses and assignments using API token authentication.

not rated 11 3mo ago A 16 tokens copy · 83% MIT

memento-flashcards

60

chemany/Mente

Skill Claude CodeCodex

Spaced-repetition flashcard system. Create cards from facts or text, chat with flashcards using free-text answers graded by the agent, generate quizzes from YouTube transcripts, review due cards with adaptive scheduling, and export/import decks as CSV.

not rated 11 3mo ago A 55 tokens copy · 95% MIT

siyuan

61

chemany/Mente

Skill Claude CodeCodex

SiYuan Note API for searching, reading, creating, and managing blocks and documents in a self-hosted knowledge base via curl.

not rated 11 3mo ago A 31 tokens copy · 94% MIT

telephony

62

chemany/Mente

Skill Claude CodeCodex

Give Mente phone capabilities without core tool changes. Provision and persist a Twilio number, send and receive SMS/MMS, make direct calls, and place AI-driven outbound calls through Bland.ai or Vapi.

not rated 11 3mo ago A 45 tokens copy · 80% MIT

bioinformatics

63

chemany/Mente

Skill Claude CodeCodex

Gateway to 400+ bioinformatics skills from bioSkills and ClawBio. Covers genomics, transcriptomics, single-cell, variant calling, pharmacogenomics, metagenomics, structural biology, and more. Fetches domain-specific reference material on demand.

not rated 11 3mo ago B 55 tokens copy · 94% MIT

domain-intel

64

chemany/Mente

Skill Claude CodeCodex

Passive domain reconnaissance using Python stdlib. Subdomain discovery, SSL certificate inspection, WHOIS lookups, DNS records, domain availability checks, and bulk multi-domain analysis. No API keys required.

not rated 11 3mo ago A 43 tokens copy · 88% MIT

drug-discovery

65

chemany/Mente

Skill Claude CodeCodex

Pharmaceutical research assistant for drug discovery workflows. Search bioactive compounds on ChEMBL, calculate drug-likeness (Lipinski Ro5, QED, TPSA, synthetic accessibility), look up drug-drug interactions via OpenFDA, interpret ADMET profiles, and assist with lead optimization. Use for medicinal chemistry…

not rated 11 3mo ago A 84 tokens copy · 86% MIT

duckduckgo-search

66

chemany/Mente

Skill Claude CodeCodex

Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Prefer the ddgs CLI when installed; use the Python DDGS library only after verifying that ddgs is available in the current runtime.

not rated 11 3mo ago A 57 tokens copy · 94% MIT

gitnexus-explorer

67

chemany/Mente

Skill Claude CodeCodex

Index a codebase with GitNexus and serve an interactive knowledge graph via web UI + Cloudflare tunnel.

not rated 11 3mo ago C 28 tokens copy · 91% MIT

parallel-cli

68

chemany/Mente

Skill Claude CodeCodex

Optional vendor skill for Parallel CLI — agent-native web search, extraction, deep research, enrichment, FindAll, and monitoring. Prefer JSON output and non-interactive flows.

not rated 11 3mo ago C 37 tokens copy · 94% MIT

qmd

69

chemany/Mente

Skill Claude CodeCodex

Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration.

not rated 11 3mo ago B 43 tokens copy · 91% MIT

scrapling

70

chemany/Mente

Skill Claude CodeCodex

Web scraping with Scrapling - HTTP fetching, stealth browser automation, Cloudflare bypass, and spider crawling via CLI and Python.

not rated 11 3mo ago A 29 tokens copy · 89% MIT

1password

71

chemany/Mente

Skill Claude CodeCodex

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in, and reading/injecting secrets for commands.

not rated 11 3mo ago A 37 tokens copy · 88% MIT

oss-forensics

72

chemany/Mente

Skill Claude CodeCodex needs its repo

Supply chain investigation, evidence recovery, and forensic analysis for GitHub repositories. Covers deleted commit recovery, force-push detection, IOC extraction, multi-source evidence collection, hypothesis formation/validation, and structured forensic reporting. Inspired by RAPTOR's 1800+ line OSS Forensics system.

not rated 11 3mo ago B 64 tokens copy · 88% MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: