GitHub Trends

#python#agent#agentic_rag#ai_agents#clawbot#context_database#context_engineering#filesystem#llm#memory#openclaw#opencode#rag#skill OpenViking is a free open-source tool that acts as a context database for AI agents, using a simple file system to organize memories, resources, and skills under viking:// paths. It fixes issues like scattered data, high token costs, weak searches, and untraceable errors with tiered loading (L0 abstracts, L1 overviews, L2 details loaded on demand), recursive directory retrieval, visual traces, and auto-session memory updates. You benefit by building smarter, cheaper agents faster—like managing files—saving up to 96% on tokens while boosting task success by 50%+. https://github.com/volcengine/OpenViking

#python#agentic_ai#agents#memory Hindsight is a top agent memory system that helps AI agents learn over time by storing facts, experiences, and mental models like human memory, beating rivals on LongMemEval benchmarks with 91.4% accuracy. Add it easily with 2 lines of code via Python or Node.js clients, using simple retain, recall, and reflect operations for Docker or embedded setups. You benefit by building smarter, consistent agents that reduce errors, cut hallucinations, handle long-term tasks, and personalize chats—saving time and boosting performance in production. https://github.com/vectorize-io/hindsight

#python#agent#ai_agents#memory#memoryscope#rag#reme ReMe is a memory toolkit for AI agents with file-based (Markdown files for easy editing) and vector-based systems to fix limited context and stateless chats. It auto-summarizes talks, saves key facts like preferences, and recalls them next time using hybrid search. Install via `pip install reme-ai`, set API keys, and use ReMeCli or Python code for smart agents. You benefit by building persistent, learning agents that remember your needs, work faster on repeat tasks, and feel more natural without starting over. https://github.com/agentscope-ai/ReMe

#python#agent#agentic_ai#agentic_framework#agentic_workflow#ai#ai_agents#ai_companion#ai_roleplay#benchmark#framework#llm#mcp#memory#open_source#python#sandbox MemU lets AI systems take in conversations, documents, and media, turn them into structured memories, and store them in a clear three-layer file system. It offers both fast embedding search and deeper LLM-based retrieval, works with many data types, and supports cloud or self-hosted setups with simple APIs. This helps you build AI agents that truly remember past interactions, retrieve the right context when needed, and improve over time, making your applications more accurate, personal, and efficient. https://github.com/NevaMind-AI/memU

#python#agent#ai#aiagent#awesome#chatgpt#hacktoberfest#hacktoberfest2025#llm#long_short_term_memory#memori_ai#memory#memory_management#python#rag#state_management Memori is an open-source memory engine that gives AI language models human-like memory using standard SQL databases like PostgreSQL, MySQL, or SQLite.[1][2] With just one line of code, you can enable any LLM to remember conversations, learn from interactions, and maintain context across sessions.[1] The key benefits are significant cost savings of 80-90% compared to expensive vector databases, complete data ownership and transparency since memories are stored in SQL databases you control, and zero vendor lock-in allowing you to export and move your data anywhere.[1][3] Memori works with popular frameworks like OpenAI, Anthropic, and LangChain, making it easy to integrate into existing projects without complex setup.[1] https://github.com/GibsonAI/Memori

#python#agent#context_engineering#electron#embedding_models#memory#proactive_ai#python#python3#rag#react#vector_database#vision_language_model MineContext is a special AI tool that helps you work more efficiently. It collects information from your computer screen and other sources, then uses this data to give you useful insights, summaries, and reminders. This helps you stay organized and focused on important tasks. MineContext is also very private because it stores all your data on your local device, not in the cloud. It's like having a personal assistant that helps you manage your digital life better. https://github.com/volcengine/MineContext

#python#ai#context#embedded#faiss#knowledge_base#knowledge_graph#llm#machine_learning#memory#nlp#offline_first#opencv#python#rag#retrieval_augmented_generation#semantic_search#vector_database#video_processing Memvid lets you store millions of text pieces inside a single MP4 video file using QR codes, making your data 50-100 times smaller than usual databases. You can search this video instantly in under 100 milliseconds without needing servers or internet after setup. It works offline, is easy to use with simple Python code, and supports PDFs and chat with your data. The upcoming version 2 will add features like continuous memory updates, shareable capsules, fast local caching, and better video compression, making your AI memory smarter, faster, and more flexible. This means you get a powerful, portable, and efficient way to manage and search huge knowledge bases quickly and easily. https://github.com/Olow304/memvid

#typescript#12_factor#12_factor_agents#agents#ai#context_window#framework#llms#memory#orchestration#prompt_engineering#rag The 12-Factor Agents are a set of proven principles to build reliable, scalable, and maintainable AI applications powered by large language models (LLMs). They help you combine the creativity of AI with the stability of traditional software by managing prompts, context, tool calls, error handling, and human collaboration effectively. Instead of relying solely on complex frameworks, you can apply these modular concepts to improve your existing products quickly and reach high-quality AI performance for real users. This approach makes AI software easier to develop, debug, and scale, ensuring it works well in production environments[1][3][5]. https://github.com/humanlayer/12-factor-agents

#python#agent_computer_interface#ai_agents#computer_automation#computer_use#grounding#gui_agents#in_context_reinforcement_learning#memory#mllm#planning#retrieval_augmented_generation Agent S2 is a smart AI assistant that handles computer tasks by breaking them into smaller steps and using specialized tools for each part, making it highly adaptable and efficient across different systems like Windows and Android. It outperforms other AI tools in completing complex tasks, learns from experience, and adjusts plans as needed, helping users automate digital work more reliably and effectively. https://github.com/simular-ai/Agent-S