freshcrate

Search results for "checkpoint"

Clear filters
34 results found (Python)
orbax-checkpointπŸ“0.11.36🌳 Mature⭐501

Orbax Checkpoint

timmπŸ“1.0.26πŸ›οΈ Flagship⭐36,678

PyTorch Image Models

PraisonAIπŸ“v4.6.27πŸ›οΈ Flagship⭐6,969

PraisonAI 🦞 β€” Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, R

synapse-aiπŸ“v1.0.0🌱 Seedling⭐41

Build AI agents that actually do things. Synapse is an open-source platform for creating, connecting, and orchestrating AI agents powered by any LLM β€” local or cloud.

Auto-claude-code-research-in-sleepπŸ“v0.4.4πŸ›οΈ Flagship⭐7,173

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

medusaπŸ“v2026.5.5🌿 Growing⭐256

AI-first security scanner with 76 analyzers, 9,600+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo

airutπŸ“v0.24.1🌿 Growing⭐73

Airut is a system for running Claude Code tasks from email and Slack. It handles workspace provisioning, container isolation, network sandboxing, session persistence, and cleanup β€” a secure foundation

awesome-cli-coding-agentsπŸ“main@2026-04-18🌿 Growing⭐244

Curated directory of terminal-native AI coding agents and the harnesses that orchestrate them. Covers open-source tools (Pi, OpenCode, Aider, Goose), platform agents (Claude Code, Codex, Gemini CLI),

pydantic-deepagentsπŸ“0.3.15🌳 Mature⭐707

Python Deep Agent framework built on top of Pydantic-AI, designed to help you quickly build production-grade autonomous AI agents with planning, filesystem operations, subagent delegation, skills, and

cyber-pilotπŸ“v3.7.0-beta🌿 Growing⭐55

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

openakitaπŸ“v1.27.9🌳 Mature⭐1,655

An open-source AI assistant framework with skills and agent architecture

galdrπŸ“v1.4.0🌱 Seedling⭐15

AI-powered development framework with task management, 41 agents, 83 skills, and MCP tools for Cursor, Claude Code, Gemini, Codex & OpenCode. File-based memory that survives across sessions.

LRATπŸ“0.0.0🌱 Seedling⭐39

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

nexoπŸ“v7.1.6🌱 Seedling⭐11

NEXO Brain β€” Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust scoring, 150+ MCP tools. Works with Claude Code, Codex, Claude Desktop & any MC

AgentlyπŸ“v4.0.9🌳 Mature⭐1,548

[GenAI Application Development Framework] πŸš€ Build GenAI application quick and easy πŸ’¬ Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow

token-saviorπŸ“v2.6.0🌿 Growing⭐586

MCP server that saves 97% of AI coding tokens β€” your AI reads code structurally, not file-by-file. Faster, cheaper, smarter.

KilnπŸ“v0.5.0🌱 Seedling⭐17

Describe it or draw it. Kiln makes it real. β€” 461 MCP tools for AI-agent-controlled 3D printing. OctoPrint, Moonraker, Bambu Lab, Prusa Link, and Elegoo.

GenericAgentπŸ“main@2026-04-21🌿 Growing⭐5,482

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

auto-deep-researcher-24x7πŸ“main@2026-04-19🌿 Growing⭐622

πŸ”₯ An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.

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 ⚑

OpenClawProBenchπŸ“main@2026-04-15🌿 Growing⭐453

OpenClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

claude-copilotπŸ“v2.10.0🌱 Seedling⭐13

Transform Claude Code into a full development team. 11 specialized agents (Architect, Engineer, QA, Security, UX, DevOps, and more), persistent memory across sessions, and 25,000+ on-demand skills. Wo

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.

0xClawπŸ“0.0.0🌱 Seedling⭐10

πŸ¦€ The first autonomous hackathon agent stop assisting and start competing (πŸ† Hackathon Champion Project).

robotsπŸ“v0.3.8🌱 Seedling⭐44

Control robots and physical hardware with natural language through Strands Agents.

Comfy-CozyπŸ“v4.0.0🌱 Seedling⭐6

AI co-pilot for ComfyUI β€” 113 tools for workflow authoring, model provisioning, and iterative rendering. Multi-provider (Claude, GPT-4o, Gemini, Ollama). Ships as MCP server or standalone CLI.

pytorch_templateπŸ“v0.3.0🌱 Seedling⭐10

AI-agent-friendly PyTorch research pipeline β€” one YAML config drives preflight, training, Optuna HPO, and real-time TUI monitoring

openchatciπŸ“v0.42.0🌱 Seedling⭐1

The localhost AI Agent Runtime -- Chat UI, Tools, RAG, and MCP in one pip install

langchain-sandboxπŸ“langchain_sandbox==0.0.6πŸ’€ Dormant⭐239

Safely run untrusted Python code using Pyodide and Deno

Mini-o3πŸ“main@2026-04-21🌱 Seedling⭐1

🧠 Enhance visual search with Mini-o3, providing state-of-the-art multi-turn reasoning and easy-to-use training code for advanced AI applications.

ComfyUI-LoaderUtilsπŸ“main@2026-04-21🌱 Seedling⭐1

πŸ”„ Optimize model loading in ComfyUI with flexible node connections and controlled sequences for better performance and memory management.