Media memory for AI agents: books, movies, music, shows, anime, podcasts, games, manga.

MCP server and CLI tool for interacting with the Wayback Machine without API keys

Safari browser automation for AI agents — native macOS, zero Chrome overhead. 98 tools via AppleScript + JavaScript.

Solve it once. From then on, your AI knows. Experience for coding agents, EU-hosted: an MCP server for Claude Code, Cursor, Copilot & Windsurf. Learns from every bug fix, commit and CI run.

Long image chats in Codex and Claude, without the lag. The model manages its own images, pulling back only what it needs, and any image you made before is one search away: just describe what you remember.

Claude Code mod: hands off to a fresh conversation when context fills up, keeps the cache warm while you're away, and turns what you teach Claude into project notes

AI mentoring fit and book: check the fit with Marian Kamenistak and book a session in 10 minutes.

DeepSeek Harness plugin: automatically adds a stable per-conversation x-opencode-session header to OpenCode / OpenCode Go provider requests — fixes 400 MissingSessionID and keeps OpenCode's session affinity / prompt-cache routing working.

Restore prior Claude Code AND Codex sessions with zero LLM calls. Cross-tool session handoff, cache-expiry prevention, real cost dashboard. One plugin, both hosts.

Memory for your AI: what you saw on screen, said in calls and worked on, searchable by agents.

Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch. Claude Code, Codex, OpenClaw, and PyPI.

Token-saving proxy for Claude Code: renders bulky context (system prompt, tool docs, old history) as dense PNGs to cut input tokens. Runs on Node and Cloudflare Workers.

Context-as-image compression proxy for LLMs: renders bulky context (system prompt, tool docs, history) as dense PNG pages with exact per-provider billing math (Anthropic/OpenAI/Gemini). Node and Cloudflare Workers. Part of the OmniRoute family.

DeepSeek Harness MCP Connector: connect servers, search tools across active connections, and troubleshoot discovery. Includes a continuously updated catalog; supports OAuth 2.0 PKCE, API keys, Streamable HTTP/stdio, and mcpServers JSON import.

Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

Context optimization for AI coding agents — lower token cost and latency without sacrificing accuracy.

vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

5,000+ Claude Code mods, with what each one can access before you install it. Context and usage meters, prompt cache warmers, status lines, guards and more, with install hints.

Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

Claude Code plugin: use ChatGPT (Codex), Cursor, OpenCode Zen, and Antigravity models inside one Claude Code session. Switch with /model, delegate to named native workers, keep each provider's own login and permissions.

Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). It keeps your proprietary data completely local, and it actually learns over time.