Search

Hugging Face Space: sema-dyslexic-assistant

GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks. With a truly usable 1M-token context window, it can handle project-level engineering context, execute long-running tasks more reliably, follow...

Publish AI agent skills to slashcmd from Codex, Claude, other agents, or the terminal.

Upload and manage HTML pages on sharedrop from the terminal

Read your markdown docs on your phone over the local network, comment by tapping a paragraph, and let your AI agent read the comments back.

Utility SDK for the ai-agent-quest project.

## Current Architecture Overview

Multi-agent coding pipeline installer for OpenCode. Install agents and skills with one command.

DeepSeek-native terminal AI agent for digital work — DeepSeek model harness analogous to Claude Code for Claude models.

Nightly GitHub/Forgejo issue orchestrator — autonomous AI agent coding tool

AI agent with streaming, tool calling, and conversation persistence. Powered by [Strands Agents SDK](https://strandsagents.com/).

Agent Discipline Layer (ADL) — keep a coding agent honest and make it prove its work: layered guardrails + a /goal contract Warden verifies against reality and signs. Claude Code today; Grok/Codex CLI/Pi planned. (formerly Claude Layers)

Local-first LLM agent with native/prompt tool calling, memory, streaming and OS automation.

Arivie Mastra agent — execute_<source> tools and optional compile_metric over the semantic layer.

CLI manager for AI agent skills presets

Long-term project memory for AI agents — decisions, features, constraints, tasks, and knowledge graph with TUI sidebar

Software 3.0 reference implementation: the OSS evaluation loop for multi-persona AI agents. 5-voice council, optional Fable 5 Oracle adjudication, Brier-audited at resolution. Maps 1:1 to Karpathy's agentic engineering job description.

AI coding agent powered by DeepSeek via browser automation — no API key needed. Performance-optimized (30-40% faster). New --headless parameter for interactive mode. Enhanced with comprehensive security.

Centralized AI agent rules for Cursor, Claude Code, Codex, and Copilot

PM Privacy Guard -- AI message privacy routing, classification, and sanitization. Self-hosted. Zero-data-retention provider routing. One-time ownership.