freshcrate

Search results for "corpus"

Clear filters
28 results found (Python)
trafilaturaπŸ“2.0.0πŸ›οΈ Flagship⭐5,758

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML.

gensimπŸ“4.4.0πŸ›οΈ Flagship⭐16,395

Python framework for fast Vector Space Modelling

ringπŸ“ring-tw-team@0.4.3🌿 Growing⭐175

89 skills and 38 specialized agents that enforce proven engineering practices for AI-assisted development. TDD, systematic debugging, parallel code review, and 10-gate development cycles β€” as a Claude

npcpyπŸ“v1.4.21🌳 Mature⭐1,307

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

Vibe-SkillsπŸ“v3.0.4🌳 Mature⭐1,645

Vibe-Skills is an all-in-one AI skills package. It seamlessly integrates expert-level capabilities and context management into a general-purpose skills package, enabling any AI agent to instantly upgr

synaptic-memoryπŸ“v0.16.0🌱 Seedling⭐27

Brain-inspired knowledge graph: spreading activation, Hebbian learning, memory consolidation.

UltraRAGπŸ“v0.3.0.2🌳 Mature⭐5,510

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

LRATπŸ“0.0.0🌱 Seedling⭐39

The implementation for SIGIR 2026: Learning to Retrieve from Agent Trajectories.

AutoRAGπŸ“v0.3.22🌳 Mature⭐4,713

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

cyllamaπŸ“0.2.11🌱 Seedling⭐25

A thin cython wrapper around llama.cpp, whisper.cpp and stable-diffusion.cpp

DeepCodeπŸ“v1.2.0πŸ›οΈ Flagship⭐15,244

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

OpenContractsπŸ“v3.0.0.b4🌳 Mature⭐1,283

Humans and AI agents, building knowledge bases together. Self-hosted document annotation, version control, semantic search, and MCP.

aragπŸ“v0.1.0🌿 Growing⭐252

A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.

spacy-loggersπŸ“1.0.5🌱 Seedling⭐12

Logging utilities for SpaCy

agentic-chatopsπŸ“main@2026-04-20🌿 Growing⭐100

3-tier agentic ChatOps (n8n + GPT-4o + Claude Code) implementing all 21 patterns from "Agentic Design Patterns" β€” solo operator managing 137 devices

yao-meta-skillπŸ“main@2026-04-19🌿 Growing⭐297

YAO = Yielding AI Outcomes. A lightweight but rigorous system for creating, evaluating, packaging, and governing reusable agent skills.

AGI-Alpha-Agent-v0πŸ“main@2026-04-18🌿 Growing⭐284

META‑AGENTIC α‑AGI πŸ‘οΈβœ¨ β€” Mission 🎯 End‑to‑end: Identify πŸ” β†’ Out‑Learn πŸ“š β†’ Out‑Think 🧠 β†’ Out‑Design 🎨 β†’ Out‑Strategise β™ŸοΈ β†’ Out‑Execute ⚑

rag-chatbotπŸ“main@2026-04-14🌿 Growing⭐407

RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.

plamenπŸ“main@2026-04-09🌿 Growing⭐220

Autonomous Web3 security audit agent for Claude Code

engram-memoryπŸ“v1.0.0🌱 Seedling⭐71

Agent memory and conflict detection platform. We're hiring contributors check HIRING.md

markdown-vault-mcpπŸ“v1.27.0🌱 Seedling⭐5

Generic markdown collection MCP server with FTS5 + semantic search, frontmatter-aware indexing, and incremental reindexing

synthadocπŸ“v0.1.0🌱 Seedling⭐66

Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-

doryπŸ“v0.1.0🌱 Seedling⭐14

One memory layer for every AI agent. Local-first, markdown source of truth, and CLI/HTTP/MCP native. Your agent forgot who you are. Again. Dory fixes that.

locallensπŸ“v0.0.3🌱 Seedling⭐7

Search your files by talking to them - 100% offline

claude-ruby-grape-railsπŸ“v1.13.4🌱 Seedling⭐5

Claude Code plugin for Ruby, Rails, Grape, PostgreSQL, Redis, and Sidekiq development

second-brainπŸ“1.0🌱 Seedling⭐461

Second Brain is a desktop application that acts as a personal knowledge base, using retrieval-augmented generation (RAG), multimodal AI models, and a hybrid lexical/semantic search algorithm to intera

pyannote-audio4.0.4🌱 Seedling

State-of-the-art speaker diarization toolkit