AI Agent2025
Provides hierarchical, versioned semantic memory for AI agents with Git-like branching, commits, and rollbacks—using semantic paths and cryptographic provenance instead of opaque vector stores. Designed for branch-aware, auditable memory in multi-agent and production workflows.
AI Agent2025
Framework for building multi-modal AI agents that watch, listen, and reason over live video, pairing vision models (YOLO, Roboflow, Moondream) with LLMs like Gemini and OpenAI. Agents join calls in ~500ms and keep audio/video latency under 30ms.
Teaches AI agent principles and practice through a structured Chinese curriculum, pairing theory with runnable code so learners can build, debug, and extend agent systems step by step.
AI Agent2025
Audits source code for security flaws using LLM agents, then auto-generates and runs proof-of-concept exploits in Docker sandboxes to confirm which findings are real. Retrieves CWE/CVE knowledge via RAG; runs on hosted or local Ollama models.
AI Infra2025
Orchestrates multiple AI providers to generate context-aware attack payloads, scan web targets for 45+ vulnerability types, and produce compliance-mapped reports. Supports dynamic provider failover, RAG-indexed CVE intelligence, browser automation, and AI triage; requires API keys and authorized testing.
AI Dataset2025
Provides mined hard negatives and relevance scores for 1.88M queries across seven retrieval datasets, enabling contrastive fine-tuning and nv-retrieve filtering; includes full 2048 mined negatives per query, paired query/document splits, and parquet-formatted files for large-scale training.
AI Agent2025
Agent memory that learns over time instead of just recalling past chats: retain/recall/reflect primitives turn interactions into facts, experiences, and mental models. Reports top LongMemEval scores; self-hostable with Python and Node SDKs.
AI Agent2025
Builds knowledge-grounded AI agents by combining hybrid RAG retrieval with a visual, block-based workflow editor, keeping question-answering tied to your own data. Supports document import, reranking, MCP, and self-hosted deployment.
AI Agent2025
Drives penetration testing from chat commands, orchestrating 100+ security tools through an MCP-native multi-agent engine on CloudWeGo Eino. Adds attack-chain graphs, risk scoring, and human-in-the-loop approval gates for authorized use.
AI Dataset2025
Aggregates SEC EDGAR filings into raw files, parsed plaintext, and rich filing metadata for LLM training and retrieval. Includes ~8.05M filings (~590 GB, ~43B tokens), per-filing token counts, and parsed outputs; Apache-2.0.
AI Infra2025
Combines a vector store, Cypher-style graph queries, and on-device LLM inference in one Rust engine, with a graph neural network that reranks results and adapts to query patterns in under a millisecond. Services ship as self-contained .rvf containers.
AI Agent2025
Forecasts how social scenarios might unfold by running multi-agent simulations: thousands of LLM agents with memory and personalities, seeded from real data, that you steer by injecting variables to 'rehearse the future' in a digital sandbox.