AI Infra2024
Builds a knowledge graph from a text corpus by extracting entities and relations, clusters it into communities with the Leiden algorithm, and summarizes them — so queries can synthesize across scattered documents instead of retrieving isolated chunks.
AI Client2024
Memory engine that lets AI apps remember users across conversations: it extracts facts, tracks updates, resolves contradictions, and auto-forgets stale info, returning context in ~50ms. Tops the LongMemEval, LoCoMo and ConvoMem memory benchmarks.
AI Agent2024
Orchestrates low-code multi-agent teams that plan, research, code and deliver results to Telegram, Discord, and WhatsApp. Includes handoffs, guardrails, memory and RAG, and integrates 100+ LLM providers via MCP for production-ready agent workflows.
Chatbot2024
Self-hostable answer engine that pairs SearxNG web search with a local (Ollama) or cloud LLM to return cited answers on your own hardware. An open-source Perplexity alternative with Speed, Balanced, and Quality modes plus image, video, and file search.
Chatbot2024
Runs a privacy-first, self-hosted answering engine that combines web retrieval with local and cloud LLMs to produce cited answers. Supports SearxNG search, file uploads, image/video search, and mix-and-match models with Speed/Balanced/Quality modes.
AI Client2024
BYOK desktop app working as a universal MCP client: run any MCP server against OpenAI, Anthropic, Gemini, Grok, Ollama and 10+ providers. Also offers prompt-anywhere, AI text commands, local-file RAG, media generation and voice input.
AI API2024
Build AI workflows once and run them across model providers — GoogleAI, OpenAI, Claude, Ollama — through one SDK. Composable primitives for RAG, tool use, and agents, plus a local dev UI for tracing and debugging, with SDKs in JS/TS, Go, and Python.
AI Infra2024
Stores and reuses LLM key-value caches across GPU, CPU, disk, and remote backends so vLLM and SGLang skip recomputing repeated context. Non-prefix reuse (CacheBlend) and PD disaggregation cut time-to-first-token for long-context and RAG serving.
AI API2024
Ingests documents, images, audio, video and web pages and converts them into structured, LLM-friendly markdown and parsed data. Runs locally (fits on a T4 GPU), supports ~20 file types, offers OCR, transcription, table extraction and a Gradio UI; deployable via Docker/Skypilot. Licensed under GPL-3.0; some model weights carry cc-by-nc-sa restrictions for commercial use.
Official code companion to the O'Reilly book by Jay Alammar and Maarten Grootendorst: 12 chapters of runnable notebooks on tokens, embeddings, Transformers, text classification, clustering, prompt engineering, semantic search, RAG, and fine-tuning.
AI Agent2024
Multi-tenant agent harness that makes enterprise knowledge retrievable, graph-reasonable, and deliverable by LLM-powered agents. Integrates RAG + a Milvus-based knowledge graph, LangGraph orchestration, and document parsing for citation-backed answers and graph reasoning; deployable via Docker (requires a compatible LLM API).