#python #ai #chromadb #llm #mcp #memory #python

MemPalace is a local AI memory tool that saves your chats as exact text, then finds useful parts with search, so nothing leaves your machine unless you choose it. It is free, open source, MIT-licensed, and works with Python 3.9+, ChromaDB, and local tools like Claude Code. The main benefit is safer, private, and more reliable memory for your projects, with no required API calls or cloud fees.

https://github.com/MemPalace/mempalace

#python #ai #apple_silicon #benchmarks #cli #command_line_tool #gguf #gpu #huggingface #inference #llm #local_llm #ollama #python #vram

whichllm helps you find the best local AI model that fits your computer, not just the biggest one that fits. It checks your GPU, CPU, and RAM, ranks models using real benchmark data, and can also simulate other hardware, plan upgrades, and start a chat with a model in one command. This saves you time and helps you pick a model that should run well and work better for your needs.

https://github.com/Andyyyy64/whichllm

#python #bert #deepseek #healthcare #ios #llm #mlx #ner #on_device #on_premise #pii #pii_detection #qwen #sovereign_ai #swift #swift_package #swiftui

OpenMed is a local-first healthcare AI that runs on your own device or server, so patient data never leaves your network. It can extract medical entities, remove personal info, and use 1,000+ medical models in Python, Swift, or REST, which helps you work faster while keeping data private and avoiding cloud costs and vendor lock-in.

https://github.com/maziyarpanahi/openmed

#other #agentic_ai #coding #llm #long_horizon

GLM-5.2 is the latest open-source model built for long, complex tasks, featuring a stable 1 million-token context that lets you handle huge projects without losing track of details. It also offers stronger coding skills with flexible thinking modes to balance speed and quality, plus faster performance. You benefit by getting reliable, high-quality results for big software engineering jobs, automated research, or long planning sessions, all while using an open model that saves costs compared to closed alternatives.

https://github.com/zai-org/GLM-5

#python #ai #ai_agents #cli #hypergraph #information_extraction #knowledge #knowledge_graph #llm #python #rag

Hyper-Extract is a tool that uses AI to turn messy documents into clean, structured knowledge like lists, graphs, and linked data with one command. It gives you fast search, easy visual reports, and ready-made templates, so you can save time, understand information faster, and keep adding new documents without rebuilding everything.

https://github.com/yifanfeng97/Hyper-Extract

#csharp #ai #ai_integration #anthropic #claude #copilot #cursor #game_development #gamedev #gemini #llm #mcp #model_context_protocol #openai #unity #unity3d #videogames

MCP for Unity lets you control your Unity Editor using natural language with AI tools like Claude, Cursor, or VS Code. You can create scenes, edit scripts, manage assets, and run tests just by typing prompts. The benefit to you is faster game development because AI automates repetitive tasks, so you spend less time on manual work and more time creating your game. It is free under the MIT license and works with any MCP client.

https://github.com/CoplayDev/unity-mcp

#python #agent_skills #agentic_ai #ai_agents #autonomous_agents #claude #claude_code #claude_skills #codex #coding_agent #context_engineering #copilot #cursor #developer_tools #github_copilot #llm_agents #long_running_agents #manus #multi_agent_systems #pi #planning

This tool makes your AI coding agent keep a plan in files like `task_plan.md` so it never loses its goals when context fills up, you run `/clear`, or it crashes. You get a working memory on disk that auto-recovers past sessions and holds the agent until the plan is truly done, letting complex, multi-step tasks finish reliably without goal drift or repeated errors.

https://github.com/OthmanAdi/planning-with-files

#typescript #agent #ai_agent #embedding #llm #local_first #long_term_memory #memory #openclaw_plugin #vector_search

TencentDB Agent Memory is an open-source system that lets AI agents remember your preferences and tasks across sessions using a 4-tier local pipeline, reducing token usage by up to 61% and boosting task success by 51%. This benefits you by saving money on AI costs, improving agent accuracy in long tasks, and ensuring your personal data stays private on your device without needing cloud services.

https://github.com/TencentCloud/TencentDB-Agent-Memory

#shell #bonsai #llamacpp #llm #mlx #prism_ml #small_models

You can run powerful Bonsai 27B AI models locally on your iPhone, Mac, or laptop without needing cloud servers. The 1-bit version fits in just 3.9 GB, allowing a 27-billion-parameter model (with vision and reasoning) to run on a phone like the iPhone 17 Pro, while the Ternary version offers higher quality at 5.9 GB. This gives you private, fast, and offline AI for chat, image analysis, and tool use, with up to 262K token context and 90–95% of full-precision performance.

https://github.com/PrismML-Eng/Bonsai-demo

#python #ai_coding #claude #claude_code #code_review #graphrag #incremental #knowledge_graph #llm #mcp #python #static_analysis #tree_sitter

code-review-graph is a free, local-first tool that builds a structural map of your code to stop AI assistants from re-reading your entire codebase, saving you significant money and time. By using Tree-sitter to parse your code into a graph and tracking changes incrementally, it identifies the exact "blast radius" of a change so your AI only reads the few files that actually matter. This reduces token usage by an average of 82x (up to 528x in best cases), cutting costs and making AI reviews feasible for massive projects like monorepos.

https://github.com/tirth8205/code-review-graph