Agent Guides plugin for Claude Code: walk Skills, walk-observer audit hooks, and the guide MCP server.

Agent Guides plugin for Hermes: per-profile walk Skills, the guide MCP server, and profile-scoped library + walk-state management.

Ask Claude "which way am I facing?" or "am I walking right now?" and it answers from your phone's motion sensors, heading, tilt, and a walking/running/stationary read, streamed from your phone's browser to your own free Cloudflare Worker.

MCP server for OpenStreetMap: geocoding, walking/driving/cycling distances, route optimization, isochrones and POI search

MCP server for OpenStreetMap: geocoding, walking/driving/cycling distances, route optimization, isochrones and POI search

chrome-devtools-mcp plus one tool: Jev walks the browser to the spot, Claude makes one devtools call there.

An AI that walks through a website like a customer and has to back every claim with a quote.

Kamakura and Enoshima trip planning tools for AI assistants (MCP): day plans, Enoden fares and passes, bloom dates, sights, walking times

The MCP server that lets an AI agent write a sidewalk walkthrough a person walks in a Chrome side panel; starts the walkd daemon if none is answering

Submit to arXiv without the headache. One command cleans your LaTeX project, catches rejection-causing errors, and walks you through the upload.

MCP server for AI agents to explore SystemVerilog, Verilog and VHDL (beta) designs: trace connectivity, walk hierarchy, jump to source - without pasting RTL into context. Built on najaeda.

A macOS desktop pet that is also an AI agent — it walks your screen, and reaches the Mac through its own approval gate.

MCP server for the On va où ? Routing API: bike, e-bike, kick scooter, motorcycle, wheelchair and walking routes across Europe, with safety indicators

MCP server for the « On va où ? » Routing API: address geocoding, and bike, e-bike, kick scooter, motorcycle, wheelchair and walking routes across Europe, with safety indicators.

chrome-devtools-mcp plus one tool: Jev walks the browser to the spot, your agent makes one devtools call there.

QuanterLab for Claude: backtest trading rules, check them with walk-forwards, scan for candidates and read QuanterLab's published studies.

Autonomous coding agent orchestration. Give it a goal, walk away, come back to finished work. Eval loops, multi-agent pipelines, DAG dependencies, crash-proof persistence.

Point it at your running app. It walks your real user flows in a real browser and tells you what is actually broken, with proof.

MCP server that walks a live VM's x86 page tables through QEMU's gdbstub and explains translations and page faults - 2-level, PAE, 4/5-level, NX, SMEP/SMAP - checked against QEMU's info tlb.

MCP server that holds an agent's plan: steps drafted and walked in order, revised as work goes, followed from other sessions. SQLite, Native AOT, a NuGet tool per platform.

ISO/IEC 42005:2025 AI Impact Assessment MCP — runs full lifecycle impact assessment across 6 phases × 7 impact categories. Cross-walks to EU AI Act + ISO 42001. By MEOK AI Labs.

Salesforce sandbox seeding CLI + MCP server — SOQL-driven org-to-org copy with dependency-graph walking, FK remapping, deterministic PII masking, and a hard AI-never-sees-your-data boundary.

Korea AI Basic Act compliance MCP — in force since 22 Jan 2026. High-impact AI + mandatory GenAI labelling + MSIT obligations + cross-walks to EU AI Act + Japan AI Promotion. By MEOK AI Labs.

Zero-dependency repo-indexing engine: deterministic walk + symbol/import extraction (tree-sitter AST with regex fallback) + typed cross-file link-graph + analytics. One vendorable engine.mjs, CLI + MCP server included.

Salesforce sandbox seeding CLI + MCP server: SOQL-scoped org-to-org copy with dependency-graph walking, cross-org FK remapping, deterministic PII masking, and a hard AI-never-sees-your-data boundary.

Ask your AI to find a flat to rent in Romania — MCP server + CLI. Live search across storia, publi24, lajumate for all 3,181 localities; heating, parking & walking distance read from the ads.

MCP server that lets AI assistants animate in OpenToonz: editable vector levels, xsheet timing, real keyframes, anatomy-accurate character rigs with walk and run cycles, physics, and studio looks built from OpenToonz fx.

MCP server bridging any LLM agent to the Serotonin Lua runtime for Roblox - lets an agent walk the live game tree, read entity state, project coordinates to screen, and run arbitrary Lua inside the cheat

Open, deterministic citation graph & search index of Japanese statutory law — 8,998 laws down to article/paragraph/item · 1.4M resolved citations · jlawcite CLI (lookup, BM25, graph walk) + MCP server + explorer

Walk a generated world, then ask it why — Hīkoi, a first-person viewer for a fully generated planet (geology, climate, hydrology, life), plus a local MCP server so your own AI can interrogate the same world. No account, no network.

LLM-native spatial middleware. Give an AI agent a map of any location on earth as a token-budgeted topological graph, with geocoding, places, walk and transit routes, indoor floors, weather, air quality, and traffic, that it can reason over directly.

Rust + WASM sublinear-time solver for asymmetric diagonally dominant systems. Exposes Neumann series, push, and hybrid random-walk algorithms with npm/npx CLI and Flow-Nexus HTTP streaming for swarm cost propagation and verification.

Lets Claude read your WHOOP data, so you can ask about your sleep, recovery and training and use it together with your calendar, web search and other connectors. You host it yourself; the setup guide walks you through it.

What was promised, by whom, and what you walk into next — a local-first macOS menu-bar app that turns recorded meetings into commitments, briefs you before the next call, and also types what you say into any app.

Autonomous QA scanner: point it at your running app and it walks the real user flows in a headless browser and reports what's actually broken: broken pages/links, console and network errors, empty/placeholder data, broken forms, state-loss, bad loading/er

AI agent that walks your site’s key journeys (purchase, sign-up, lead) in a real browser and checks that GA4, Google Ads, Meta and TikTok tags fire correctly. Works from the CLI or as an MCP server in your AI app.

Unofficial read-only MCP server for Neshan, the map of Iran: place search, reviews, photos and menus, nearby places, reverse geocoding, air quality, car, bike, walking and bus/metro directions, travel times and Tehran traffic-zone checks for Claude, Cursor and Copilot. No API key. نقشه نشان

Free your Mi Bands, Garmin watches & Under Armour footpod! OmniBandBridge (OBB) tracks real-time running & walking data (cadence, speed, stride) from your wereable. Use it on Zwift, treadmills, or outdoors. Integrates FTMS speed/incline and HR to compute personalized metabolic power. Join our community to report bugs and suggest features!

Desktop market-analysis workbench you drive by talking to an AI agent. A local Python sidecar does the work - indicators, candlestick and chart patterns, walk-forward backtests, volatility/regime forecasts, DeFi P&L - as 59 MCP tools; an Electron viewer draws it live. Read-only research and labeled advice: no broker, no orders.

MCP server + NinjaTrader 8 AddOn that gives an AI coding assistant eyes and a build loop for NinjaScript: compile with structured errors, chart and Print reads, headless backtests, walk-forward, lint, trade match vs research, screenshots. Opt-in Sim-only order and strategy control, plus Sim desk crash-recovery tools. Read-only by default.

Agentic control layer for the Censurado self-hosted AI news portal: a stdlib Python CLI plus an MCP server (32 tools) an LLM agent drives to write and publish AI-persona articles through a gated editorial walk, curate the front page and authors, and deploy. Ships the prompt/skill recipe and a 24/7 serve loop.

Provider-neutral prompt calibration engine with sensitivity-ranked meta-axes, hard-gate x soft-score fitness, walk-forward ship gates, guarded/expedition profiles, and explicit capability/risk reporting across Anthropic, OpenAI, Gemini, and local OpenAI-compatible backends. Optional sub-tools (mini-omega-lock, mini-antemortem-cli) distribute separately and plug in via the omegaprompt.preflight interface.

A text editor for LLMs, not humans. Take ed, the line editor that nobody has voluntarily used since about 1975, and rebuild it for an environment where the typing user is a language model. Short verbs, line addresses, no modes, no TUI. What an editor optimises for changes when the user is the model: round trips per task, tokens per command, an editing buffer with a long memory, and an undo tree that remembers the branches the agent abandoned, because that's often where the interesting work was. ## Features - **Fewer round trips.** Read-before-Edit is unnecessary; on conflict the response carries the new content so you reconcile in one call instead of pre-reading every time. - **Branching undo.** Walked-back work stays addressable instead of being thrown away when you pick a different path. - **Three-way merge.** Concurrent agents get a structured conflict response instead of a silent overwrite. - **Atomic batches.** Multi-file refactors run all-or-nothing instead of leaving half-applied state on failure. - **Cross-file moves and regex replace as primitives.** Operations the built-in tools can't express cleanly become single calls. - **Drift detection.** External edits to an open file are folded into the tree instead of being clobbered by the next write. - **Inline diagnostics.** Type errors and lint findings surface on save, not at the next build many edits later. - **Cross-session memory.** Per-file notes persist between sessions and surface inline on the next open. - **Audit log.** Every operation recorded with actor and timestamp, so two agents in one workspace can't argue about who moved the head. ## Multi-workspace (v0.4.0) One MCP server registration handles every project you mention. Tool calls route to the workspace owning the absolute path you pass; each project gets its own SQLite, its own undo tree, its own LSP daemon — lazily spawned on first touch. Desktop hosts (Claude Desktop, Codex Desktop, Cursor) install the server once globally and use it across projects without per-project config. ## Install `ae` must be installed locally; this MCP bundle registers `ae serve` as a stdio server. ```sh brew tap frane/tap && brew install agented # or curl -sSL https://raw.githubusercontent.com/frane/agented/master/install.sh | sh ``` Pure Go, single static binary, Apache 2.0. Source: https://github.com/frane/agented

Sparse linear solvers (Neumann, Jacobi, Gauss-Seidel, conjugate gradient), PageRank and local push as an MCP server, CLI and library. Zero-dependency core: @ruvnet/sublinear-core.