AI Infra2026
Provides a reliability layer for self-hosted LLM tool-calling and multi-step agent workflows. Adds guardrails — rescue parsing, response validation, retry nudges, and a synthetic respond tool — and ships a Drop-in OpenAI-compatible proxy plus a WorkflowRunner for structured loops.
AI Infra2026
A Chromium binary patched at the C++ level to evade bot-detection and serve as a drop-in Playwright/Puppeteer replacement. Notable features: source-level fingerprint patches, human-like input emulation, auto-updating binaries, and integrations for Python/Node.js and Docker — useful for scraping, agent-driven browsing, and stealth automation.
AI Infra2026
Runs autonomous AI agents in isolated containers with declarative YAML policies that enforce filesystem, network, process, and inference controls. Provides credential providers, inference routing, hot-reloadable network/policy updates, and formal verification of policy changes for auditable agent execution.
AI Deploy2026
Runs local AI models on Apple Silicon as an OpenAI‑compatible server, emphasizing low latency, prompt caching, and reliable tool-calling. Optimized for M1–M4 Macs with multimodal support and drop‑in compatibility for IDEs and agent frameworks.
AI Model2026
Identifies and surgically removes the internal activation directions that trigger refusal behavior in large language models, with one-click options on a HuggingFace Space or a local Python API. Combines multiple extraction methods (SVD, whitened SVD, sparse autoencoders), reversible steering, and analysis-informed verification to quantify capability and refusal trade-offs.
AI Infra2026
Visualizes live global data on a CesiumJS 3D globe via a plugin-driven pipeline and real-time WebSocket DataBus. Supports dynamic plugin marketplace, an opt-in Agent Bus for external LLM/MCP control, and self-hosting with Docker and PostgreSQL.
AI Agent2026
Lets an LLM autonomously propose, edit, run, and evaluate short single‑GPU LLM training experiments — fixed 5‑minute runs (~12 experiments/hour). Agent edits a single train.py; humans supply goals via program.md. Single‑GPU, val_bpb metric.
AI Infra2026
Measures multiline text layout and block height without triggering browser reflow: it measures text segments once via Canvas+Intl.Segmenter and caches widths, then computes line breaks with pure arithmetic. Useful for streaming AI text, virtualization, and custom per-line rendering.
AI Infra2026
Provides a single persistent database and open protocol so multiple AI tools share the same memory — built-in vector search, an AI gateway, and capture/skill extensions. Best for teams and power users who want a unified, self-hosted agent memory instead of siloed notes or per-tool caches.
AI Agent2026
Turns a single research idea into runnable experiments and a conference-ready paper by orchestrating an LLM-driven end-to-end workflow (literature → design → code → sandboxed runs → analysis → writing). Provides human-in-the-loop checkpoints, domain-specialist executors, and multi-layer citation verification.
AI Agent2026
Provides a persistent, typed semantic memory layer for AI agents—supports remember, recall, and answer primitives so agents retain long-term context. Writes are instantly searchable and retrieval uses an information-theoretic engine, avoiding separate vector DBs or indexing delays.
AI Infra2026
Compresses high-dimensional embeddings into low-bit TurboQuant indexes for fast, memory-efficient local vector search. Supports online ingest (no train/rebuild), SIMD kernels that match or beat FAISS, per-vector length-renormalization, and runtime allowlists — suited for privacy-sensitive, low-latency RAG.