AI Agent2024
Open-source platform for autonomous coding agents that work like developers: editing files, running shell commands, browsing the web, and calling APIs in an isolated sandbox. Model-agnostic, with GitHub, Slack, and CI/CD integration.
AI Infra2024
kvcache-ai (maintainers / MADSys group, Tsinghua University & contributors)MADSys Lab, Tsinghua University, Approaching.AI +1
Runs huge mixture-of-experts LLMs like DeepSeek-R1/V3 on a single 24GB GPU plus CPU DRAM by keeping attention on the GPU and offloading expert weights to CPU. Reports 3-28x speedups via Intel AMX/AVX512 kernels and fits 139K context in 24GB VRAM.
AI Client2024
Connects any LLM to internal knowledge sources and lets teams chat with cited, RAG-style answers. Notable for broad connectors (Drive, Notion, GitHub, YouTube), universal LLM/embedding support, and self-hostable Docker deployment — aimed at teams that need private, searchable LLM-backed knowledge.
AI Image2024
Turns a UI screenshot into structured elements so a vision LLM can act without HTML or accessibility trees. A fine-tuned detector finds interactable icons; a caption model describes their function, lifting GPT-4V grounding on ScreenSpot and Mind2Web.
AI Infra2024
Official inference framework for 1-bit and ternary (1.58-bit) LLMs such as BitNet b1.58, with optimized CPU kernels. Delivers 1.37x-6.17x speedups and 55-82% lower energy on x86 and ARM, and runs a 100B model on a single CPU at 5-7 tokens/sec.
AI Audio2024
Chains four swappable open modules — voice activity detection, speech-to-text, an LLM, and text-to-speech — into a local voice agent that needs no proprietary APIs. Runs on CUDA, Apple Silicon, or Docker, with an OpenAI-compatible realtime WebSocket mode.
AI Agent2024
Developer framework for building AI agents that autonomously trade on Polymarket prediction markets. Bundles the Polymarket and Gamma APIs, a Chroma RAG layer that pulls in news, and a CLI to query markets, reason with an LLM, and execute trades.
AI Infra2024
Runs local LLM, vision-language, ASR, OCR, and image-generation models across NPU, GPU, and CPU from one command. Differs from Ollama and llama.cpp with first-class Qualcomm Hexagon NPU support and day-0 coverage of new models like Qwen3-VL.
AI Train2024
Trains a sub-100M-parameter LLM from scratch — pretraining, SFT, LoRA, DPO/RLHF, and distillation, sized from ~26M up to ~100M-plus dense and MoE. Headline figure: the ~64M minimind-3 variant's SFT stage runs 1 epoch in ~2h and ~3 RMB on one NVIDIA 3090.
AI Agent2024
Stores agent memory as human- and agent-readable Markdown files with wikilinks instead of an opaque vector DB. Auto Memory/Resource/Dream jobs distill conversations into long-term notes, and hybrid wikilink + BM25 + embedding search retrieves them.
AI Client2024
Desktop finance analytics terminal that combines CFA-level models, real-time trading and 100+ data connectors with embedded Python for analytics; includes 37 AI agents and local/multi-provider LLM support for automated research and decision workflows.