Less AI, less Slop. Kitsuvo plugins, MCP tools and browser extensions. First no-AI web browser, free for Mac and Windows.

A slightly-less-basic implementation of persistent memory over MCP using a local knowledge graph.

Download-only BitTorrent client in Rust: ~20 MiB RAM, ~4x less CPU than Transmission, a live terminal UI and an MCP server for LLMs

MCP Server for persistent code indexing. Gives AI assistants (Claude, Gemini, Copilot, Cursor) instant access to your codebase. 50x less context than grep.

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

Run more agents with less babysitting. latch holds every agent to your own ratified decisions — and the paths you've ruled out.

Evidence-first entity and knowledge graph MCP server for AI agents to verify claims, trace cryptographic provenance, and retrieve 90% less context.

MCP Server for persistent code indexing. Gives AI assistants (Claude, Gemini, Copilot, Cursor) instant access to your codebase. 50x less context than grep.

MCP server where AI agents write sandboxed Python against 5 FDA/NIH drug APIs. 2 tools, 714 tokens, 102x less data to the model.

MCP server that lets AI agents understand any local dataset (CSV, Parquet, JSON, Excel) without reading raw rows — types, nulls, ranges and data-quality flags at ~100x less context.

Less admin, more games. AI agent tools for Codecks.io — CLI-first for token efficiency, 52 MCP tools for power users. Also a standalone CLI and Python API.

Signal is a Slack agent that makes work chat less overwhelming and more understandable for people with ADHD and autism—using AI to translate social tone, smart search to answer "what did I miss?", and calendar integration to protect focus time.

Permissionless wallet infrastructure for AI agents. Create wallets, sign transactions, and broadcast on EVM + Solana. Pay and accept x402 payments. Built-in guards. No KYC. Up to 50% less expensive than Coinbase.

Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, more familiar output.

Native Safari browser automation for AI agents. 98 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chrome DevTools MCP with 40-60% less CPU/heat on Apple Silicon.

Deterministic navigation maps over code AND markdown for AI agents — one MCP server, two lenses (tree-sitter TS/JS/Python + markdown). map the whole project, read one function or one doc-section, 99% less context. Merges codelens + docslens.

Notion MCP server with token auth: connect Claude Code, Claude Desktop, Cursor, VS Code and Codex to Notion pages, databases, comments and files. 3 tools, 94% less context than the official server, works on any plan, runs headless.

A private decoupling layer between AI and any database or dataset. The connection stays on your side, the AI can't write SQL, and it can only read views you approve. Sometimes less is more.

MCP server that hands off coding sessions across Claude Code, Codex, Cursor, Copilot, OpenCode and Antigravity. Gemini reads the old transcript so your agent doesn't have to: ~25x less context. Per-project memory, secrets redacted, zero dependencies.

Less time on rig chores, more time flying and racing. A free Windows app for flight and racing sim rigs: set up your controls and screens, learn what every button does, get everything running before you launch, and put your desk back after.

pcap/pcapng analysis as an MCP server — a digest-pinned tshark runs in a network-less Podman container with the capture mounted read-only, so an agent narrows a GB-scale capture step by step under explicit bounds instead of drowning in tshark -V. Wire content is framed as untrusted

Append-only agent journal, gated mode passports and a document index in one MCP server. Keeps 1,558 specs and reports (4.5M tokens) out of context: 123 tokens of metadata per document, drift caught by SHA256, 95.75% less to read.

Shiplogue is an open-source, local-first developer tool that turns your coding activity into clear daily stand-ups. It captures work from your IDE, Git, GitHub, and AI coding agents to generate structured standups—so you spend less time writing status reports and more time building.

Apache Camel routes in Rust, and the reliable action layer for AI agents: routes as MCP tools with schema checks, approvals, run-once and audit. ~230 components, std-only, one native binary: 3 ms startup, up to 54x less memory, 1.7-8.7x Camel's throughput. A Cameleering project.

Self-hosted MCP server running multi-step Claude agent pipelines: ingest artifacts into reusable knowledge bases, generate structured documents (SOW/BRD/HLD) and configs (JSON/YAML/XML), write SDK integration code from API docs, automate workflows on API-less websites via browser, and execute live API sequences from specs.

Free MCP server and agent skill that runs, diagnoses and fixes failing Playwright tests (TypeScript and pytest), and proves each fix by re-running it. Flaky verdicts, finds the commit that broke a test, blocks fixes that check less, posts CI fixes as PR suggestions, accessibility and Web Vitals audits. MIT, no account.

css graph for AI Agent

CSS intelligence for AI coding agents — surgical style context, fewer tool calls, faster answers. 100% local.