Search that learns from feedback, over text and images: embeds locally, sends DNA only vectors.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

Hash-anchored read/edit/undo_last_edit tools for DeepSeek Harness (dsh). Every line gets a unique 3-char hash (A-Za-z0-9) that stays stable across edits; stale or ambiguous anchors are rejected, never fuzzy-matched. Undo persists across restarts.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

Generative art skill for Claude Code — deterministic, hash-seeded, onchain-ready

Discover Agent Skills in configured local directories, plugin marketplaces and Git sources. Load them through DeepSeek Harness or a local stdio MCP server, with catalog budgets, content hashes and delivery receipts.

Verify that browser profiles are actually isolated from one another instead of assuming it - confirm each profile's timezone agrees with its own exit IP, that WebRTC exposes only the proxy, that canvas and WebGL hashes stay identical across relaunches of one profile, and that no two profiles share a

Discover Agent Skills in configured local directories, plugin marketplaces and Git sources. Load them through DeepSeek Harness or a local stdio MCP server, with catalog budgets, content hashes and delivery receipts.

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

Enables MCP clients to create and control persistent, PTY-backed terminal sessions on macOS: launch commands and interactive programs, read output incrementally via byte cursors, send keystrokes, wait on conditions, and detect running/awaiting-input/exited states. Sessions run inside a Seatbelt sandbox with command policies, human approvals, secret redaction, and hash-chained audit logging.

Enables local, evidence-led analysis of a master recording into inspectable stems, timing, beats, harmony, lyrics, MIDI and sonic evidence, then finds complete-bar loopable sections for Shorts and other short-form video. Results stay traceable through source hashes, manifests, JSON/TSV/NPZ artifacts and portable Sonic Visualiser sessions, and it can run as a CLI, Python library, web service, container or MCP plugin.

An MCP server that lets any MCP client run or join a governed MACP Decision session, enforcing who may propose, vote and commit, and returning a binding Commitment whose hash anyone can recompute.

Enables agents to download single model weight files from Hugging Face repositories or Civitai model versions directly into allowlisted ComfyUI model folders. Source identifiers, destination categories, and file extensions are validated, and existing files are never overwritten.

The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.

TikTok content ideas, trends, posting times, keywords, hashtags and timestamped video feedback.

Enables ChatGPT to interact with registered T3 Code projects through an authenticated MCP endpoint, supporting directory listing, hash-checked file reads/writes, Git status/diff inspection, and opt-in package scripts.