freshcrate

Search results for "consistency"

Clear filters
48 results found (Python)
timm๐Ÿ“1.0.26๐Ÿ›๏ธ Flagshipโญ36,678

PyTorch Image Models

celery๐Ÿ“5.6.3๐Ÿ›๏ธ Flagshipโญ28,393

Distributed Task Queue.

story-shot-agent๐Ÿ“v0.2.4๐ŸŒฟ Growingโญ52

ๅ‰งๆœฌๅˆ†้•œๆ™บ่ƒฝไฝ“๏ผˆPenShot๏ผ‰๏ผšๅ‰งๆœฌโ†’ๅˆ†้•œโ†’็‰‡ๆฎตโ†’prompt | ๅŸบไบŽ LangGraph+LLM๏ผŒ่‡ชๅŠจ่งฃๆžไปปๆ„ๆ ผๅผๅ‰งๆœฌ๏ผŒ็”Ÿๆˆ Sora/Veo/Runway ็ญ‰ๆจกๅž‹ๅฏ็”จ็š„่ฟž่ดฏtext-to-videoๆ็คบ่ฏใ€‚ไฟๆŒ่ง’่‰ฒ/ๅ‰งๆƒ…่ทจ็‰‡ๆฎตไธ€่‡ด๏ผŒๆ”ฏๆŒ MCP/REST API/ๅ‡ฝๆ•ฐ่ฐƒ็”จ | Pythonๅบ“ + A2A้›†ๆˆใ€‚๏ผˆLLM-powered screenplay-to-video-prompt a

launchdarkly-server-sdk๐Ÿ“9.15.1๐ŸŒฑ Seedlingโญ44

LaunchDarkly SDK for Python

llm-wiki๐Ÿ“v1.1.0-rc8๐ŸŒฟ Growingโญ139

LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern โ€” implemented and shipped.

agentscope-runtime๐Ÿ“v1.1.5๐ŸŒณ Matureโญ744

A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.

claude-code-plugins-plus-skills๐Ÿ“v4.26.0๐ŸŒณ Matureโญ1,995

423 plugins, 2,849 skills, 177 agents for Claude Code. Open-source marketplace at tonsofskills.com with the ccpi CLI package manager.

mcp-client-for-ollama๐Ÿ“v0.28.0๐ŸŒณ Matureโญ655

A text-based user interface (TUI) client for interacting with MCP servers using Ollama. Features include agent mode, multi-server, model switching, streaming responses, tool management, human-in-the-l

Auto-claude-code-research-in-sleep๐Ÿ“v0.4.4๐Ÿ›๏ธ Flagshipโญ7,173

ARIS โš”๏ธ (Auto-Research-In-Sleep) โ€” Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in โ€” works wi

openclaw-superpowers๐Ÿ“main@2026-04-17๐ŸŒฟ Growingโญ56

44 plug-and-play skills for OpenClaw โ€” self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and MCP health monitoring. Your agent teaches itself new

monocle๐Ÿ“v0.7.8๐ŸŒฟ Growingโญ79

Monocle is a framework for tracing GenAI app code. This repo contains implementation of Monocle for GenAI apps written in Python.

parlant๐Ÿ“v3.3.1๐Ÿ›๏ธ Flagshipโญ17,999

The conversational control layer for customer-facing AI agents - Parlant is a context-engineering framework optimized for controlling customer interactions.

The Multi-Agent Custom Automation Engine Solution Accelerator is an AI-driven system that manages a group of AI agents to accomplish tasks based on user input. Powered by Microsoft Agent Framework, Az

cyber-pilot๐Ÿ“v3.7.0-beta๐ŸŒฟ Growingโญ55

Cyber Pilot is a traceable delivery system for requirements, design, plans, and code.

mcp-gateway-registry๐Ÿ“v1.0.18๐ŸŒณ Matureโญ599

Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding a

animaworks๐Ÿ“v0.6.2๐ŸŒฟ Growingโญ230

Organization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).

Engram๐Ÿ“v1.0.0๐ŸŒฟ Growingโญ71

Multi-agent memory consistency platform. We're hiring contributorsโ€”check HIRING.md

basic-memory๐Ÿ“v0.20.3๐ŸŒณ Matureโญ2,899

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

pathway๐Ÿ“v0.30.0๐Ÿ›๏ธ Flagshipโญ63,440

Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.

claude-codex-settings๐Ÿ“v2.3.0๐ŸŒณ Matureโญ623

My personal Claude Code and OpenAI Codex setup with battle-tested skills, commands, hooks, agents and MCP servers that I use daily.

LIA-Assistant๐Ÿ“v1.17.1๐ŸŒฑ Seedlingโญ17

Open-source multi-agent AI assistant powered by LangGraph, FastAPI & Next.js โ€” 16+ agents, Human-in-the-Loop, MCP integration, voice TTS, RAG, 500+ metrics, 6 languages.

apple-mail-mcp๐Ÿ“v0.4.1๐ŸŒฑ Seedlingโญ45

๐Ÿค– MCP server for Apple Mail - Manage emails with AI using Claude Desktop. Search, send, organize mail with natural language.

LightAgent๐Ÿ“v0.5.0๐ŸŒณ Matureโญ876

LightAgent: Lightweight AI agent framework with memory, tools & tree-of-thought. Supports multi-agent collaboration, self-learning, and major LLMs (OpenAI/DeepSeek/Qwen). Open-source with MCP/SSE prot

DeepCode๐Ÿ“v1.2.0๐Ÿ›๏ธ Flagshipโญ15,244

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

banana-claude๐Ÿ“v1.4.1๐ŸŒฟ Growingโญ331

AI image generation skill for Claude Code -- Creative Director powered by Gemini

engram-memory๐Ÿ“v1.0.0๐ŸŒฑ Seedlingโญ71

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

honcho๐Ÿ“main@2026-04-21๐ŸŒฟ Growingโญ2,721

Memory library for building stateful agents

awesome-opensource-ai๐Ÿ“main@2026-04-20๐ŸŒฟ Growingโญ2,849

Curated list of the best truly open-source AI projects, models, tools, and infrastructure.

skills-vote๐Ÿ“main@2026-04-19๐ŸŒฟ Growingโญ50

The Next-Gen Agent-Native Skill Recommendation Engine

statsig๐Ÿ“0.71.6๐ŸŒฑ Seedlingโญ9

Statsig Python Server SDK

uipath-ai-skills๐Ÿ“0.0.0๐ŸŒฑ Seedlingโญ81

AI skills that turns coding agents into UiPath experts.

Project_Infinity๐Ÿ“main@2026-04-21๐ŸŒฑ Seedlingโญ29

Project Infinity leverages MCP and Graph RAG to turn LLMs into a professional D&D 5e Game Master, governed by a dedicated dice server and a persistent player database for a truly consistent adventure.

pdca-framework๐Ÿ“v1.0.2๐ŸŒฑ Seedlingโญ25

Human-supervised AI code generation using Plan-Do-Check-Act methodology with TDD and refactoring. Works as Claude Code skill or standalone prompts.

pipulate๐Ÿ“voice-synthesis-breakthrough๐ŸŒฑ Seedlingโญ11

Local First AI SEO Software on Nix, FastHTML & HTMX

claude-ruby-grape-rails๐Ÿ“v1.13.4๐ŸŒฑ Seedlingโญ5

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

openclaw-model-bridge๐Ÿ“main@2026-04-21๐ŸŒฑ Seedlingโญ9

Connect any LLM to OpenClaw โ€” production-tested middleware for Qwen3-235B and beyond

nano-banana-pro๐Ÿ“v2.60.0-alpha๐ŸŒฑ Seedlingโญ3

# Manga-Autonoma (powered by nano-banana-2)ใ€€Autonomous AI 4-panel manga production system using Gemini API. / Gemini APIใ‚’ๆดป็”จใ—ใŸใ€ๅฎŒๅ…จ่‡ชๅพ‹ๅž‹AI4ใ‚ณใƒžใƒžใƒณใ‚ฌๅˆถไฝœใ‚ทใ‚นใƒ†ใƒ ใ€‚

AITP-Research-Protocol๐Ÿ“v0.1.0-alpha๐ŸŒฑ Seedlingโญ8

AITP Research Charter and Protocol: a charter-first protocol, contract, and adapter surface for AI-assisted theoretical physics research.

Nightshift๐Ÿ“v0.0.7๐ŸŒฑ Seedlingโญ1

Autonomous overnight codebase improvement agent for Claude Code. Run it before bed, wake up to production-ready fixes.

prd-taskmaster๐Ÿ“v3.0.0๐ŸŒฑ Seedlingโญ196

AI-powered PRD generation for Claude Code with taskmaster integration

aitoolman๐Ÿ“main@2026-04-20๐ŸŒฑ Seedlingโญ4

Controllable and Transparent LLM Application Framework

geon-decoder๐Ÿ“main@2026-04-11๐ŸŒฑ Seedlingโญ3

GEON: Structure-first decoding via equivalence classes and field closure

KAG๐Ÿ“v0.8.0๐Ÿ’ค Dormantโญ8,688

KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge base

security-controls-mcp๐Ÿ“v1.1.0๐ŸŒฑ Seedlingโญ1

MCP server for 28 security frameworks (ISO 27001, NIST CSF 2.0, NIST 800-53, SOC 2, IEC 62443)

brand-consistency-ai-skill๐Ÿ“main@2026-04-21๐ŸŒฑ Seedlingโญ1

Ensure marketing content stays on-brand by using AI to generate, audit, and validate materials across platforms with any large language model.

mockloop-mcp๐Ÿ“v2.2.9๐Ÿ’ค Dormantโญ15

Intelligent Model Context Protocol (MCP) server for AI-assisted API development. Generate mock servers from OpenAPI specs with advanced logging, performance analytics, and server discovery. Optimized