—

Autonomous Cognitive Amplifier for AI Coding Agents — CPG AST Radar, Sandboxed RLM, OKF Semantic Memory & Swarm Concurrency

Generate a visual system architecture diagram (WORKFLOW.html) with concurrency capacity estimates and bottleneck analysis from any codebase — CLI + MCP server, stdlib-only scanner.

SQLite-based MCP memory server with WAL mode for concurrent access. Drop-in replacement for @modelcontextprotocol/server-memory

SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-machine bridge sync

Verify each git tree once. A stack-agnostic verification queue and cache for parallel coding agents: bounded concurrency, per-tree result cache, request coalescing, CLI for git hooks and an MCP server for agents. Rust.

A production-grade knowledge base operating system — AI agents compile raw sources into persistent, cross-linked Markdown wikis with concurrency control, multi-provider LLM integration, FTS5 search, and community detection. One repo. Any agent. Any machine.

Compiler-grade multi-file security, business-logic & concurrency verifier in Rust. Traces cross-file taint via an O(V+E) Guard-Set Lattice (TS/JS/Go/Python/Rust), proves exploits in a Linux Bubblewrap sandbox, and exposes a stdio MCP server.

Fleet-wide shared rate limiter for A2A + multi-MCP deployments. Most MCP servers rate-limit independently — a hostile agent hitting 10 MCPs gets 10x quota. This MCP is the shared counter: every MCP checks here before allowing a call. Sliding window + concurrency grants + signed enforcement attestations. By MEOK AI Labs.

Agent-native knowledge compiler — 27 CLI commands, 15 MCP tools, 10 domain packages. AI agents turn raw documents into persistent, cross-linked Markdown wikis with modular architecture, concurrency control, multi-provider LLM support, hybrid search, entity resolution, claims tracking, Louvain/Leiden community detection, grounded 'ask this wiki' QA, and contradiction-aware evidence confidence

Durable execution and named concurrency queues for coding agents

Asynchronous two-way messaging between concurrent Claude Code and Cowork sessions.

Shared code intelligence for agent fleets — AST-aware semantic search + multi-agent memory with git-concurrent coordination

Adversarial Co-Generation Engine — concurrent Builder+Breaker agents for production-grade AI code security

Shared code intelligence for agent fleets — AST-aware semantic search + multi-agent memory with git-concurrent coordination

Messaging between concurrent AI coding sessions, across clients, over MCP. Zero infrastructure. (YAAC: Yet Another Agentic Chat.)

MCP server that captures TradingView chart images via Selenium — supports any ticker/interval with browser pooling for concurrent performance

MCP server for Microsoft Planner via Microsoft Graph — plans, buckets, and tasks (create, update, assign, complete) with automatic ETag concurrency handling

A high-performance MCP (Model Context Protocol) vector database implemented in Erlang/OTP, designed to take full advantage of the Actor model and OTP supervision trees for fault-tolerant, concurrent vector operations.

Version control for Copado Release Data Templates: snapshot, readable diff, safe concurrent edit, verified restore, PR review, lint, Agent Skill and MCP server. An Agentia CLI plugin.

The High-Performance, Hardware-Adaptive Knowledge Engine for MCP Agents: Hybrid Graph-RAG & Atomic Concurrency Control.

Use Claude subagents in Codex via an MCP server with parallel delegation across up to four concurrent agents.

Lightning-fast web search API in Rust — scrapes Brave and Yahoo concurrently, returns normalized JSON. No API keys required. Runs as HTTP or MCP server for AI agents.

Full-stack security, performance & schema diagnostic sniffer for Supabase & PostgreSQL — RLS initPlan, Supavisor :6543, missing indexes, Splinter parity, CONCURRENTLY fixes, pentest & MCP.

YAAC: yet-another-agentic-chat. Messaging between concurrent AI coding sessions, across clients, over MCP. Zero infrastructure.

Doco CLI and MCP server — one command to connect your AI agent to your knowledge base. Block-level addressing, optimistic concurrency, 29 MCP tools.

Event-driven MCP bridge for orchestrating ZCode, OpenCode, and Pi through a unified agent-* toolset, with concurrent runs, resource leases, session recovery, and backend-aware permissions.

Buildev — Open-source AI-native design-to-code platform. Visual canvas + IDE mode, multi-framework code export (React, Vue, Flutter, SwiftUI, etc.), concurrent AI agents, MCP server, and Git integration. Design visually, export clean code, zero vendor lock-in.

Steam connector for monthly concurrent players of a game, and for the games with the most live players right now. Add it to Claude, ChatGPT or Cursor in one click (MCP). Free plan.

Multi-tenant chaos-engineering / API-resilience control plane, demonstrating fault injection, optimistic concurrency, Kafka-driven execution, and distributed-systems resilience. Java 21, Spring Boot 4, Kafka, transactional outbox, CAS fencing, embedded MCP server. Lab benchmarks only.

Stadium & arena ticketing built as a reference-grade Clean Architecture solution - .NET 10, DDD, CQRS, transactional outbox/inbox, optimistic concurrency, Keycloak, Elasticsearch, Stripe, .NET Aspire - with an AI layer: an MCP server, an evaluated agent and a RAG policy assistant on pgvector.

Universal Multi-Agent Mesh State Blackboard & Conflict Deconfliction Engine. Coordinates shared multi-agent state spaces, detects concurrent mutation race conditions, executes vector clock synchronization, and resolves conflicting decisions using consensus arbitration.

Production-ready MCP memory server with SQLite WAL for thread-safe concurrent access. Drop-in replacement for @modelcontextprotocol/server-memory. Prevents race conditions and data loss in multi-session AI agent environments. ACID-compliant knowledge grap

Its fetchers bypass anti-bot systems like Cloudflare Turnstile out of the box. And its spider framework lets you scale up to concurrent, multi-session crawls. 🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

An MCP server fronting a plain-markdown vault for durable, multi-tenant agent memory. One server process serves many agents concurrently; each tool call carries its own scope (agent, user, …) so files are namespaced on disk while a human can still browse and hand-edit the vault directly with any editor.

Scan C/C++/Go/Python/Java/Rust/etc. codebases and generate directed call graphs with call ordering, conditions, conditional compilation paths, concurrency analysis, and confidence classification. Designed to give LLM agents global-to-local code understanding — first load a compact context pack, then drill into specific functions on demand.

Your Obsidian vault as Claude's second brain: self-hosted MCP connector for claude.ai, Claude mobile/Desktop and Claude Code. Links & backlinks, tags, frontmatter queries, daily notes, templates, canvases, safe concurrent edits. Local-first Markdown, no RAG. Docker + Cloudflare tunnel, OAuth 2.1.

Load-tested Isolyth's MCP tool-calling endpoint with 100 concurrent virtual users via Locust, sustaining ~535 req/sec at p95 latency of 160ms with 0% error rate; benchmarked WASM-sandboxed code execution against plain tool calls, showing only ~15-30ms of added latency overhead from sandboxing —proving security isolation came at min performance cost

⚙️ Industrial-grade pure TypeScript STL ➔ 100% Watertight Solid STEP AP242 B-Rep & CAD Features JSON engine with built-in MCP server for AI agents. Features exact Gauss-Mirtich 3D inertia, ISO threads (M2–M24), boundary unification (no extra lines), Zero-GC speed, DWRR concurrency & 5-gate RSVS reality verification across macOS, Linux, and Windows.

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

An MCP server for parallel browser automation by AI agents with multiple cloud providers

Leases with fencing tokens for agents sharing one working tree. Windows-safe, no daemon, zero runtime dependencies.

⚡ Crash-consistent Two-Phase Commit (2PC) & WAL engine for AI agent workflows. Zero dirty state, zero hallucinated rollbacks.

Android emulator for AI agents: light (1.4 GB RAM per device), a text screen outline instead of screenshots, per-device network, battery, location, screen and Android version. CLI + MCP server.

Why is this Go program stuck? MCP server and CLI that reads a goroutine dump and finds leaks, lock pile-ups and full database pools. Never connects to your service.

An MCP server for a product catalogue: bounded tools, version-checked writes with dry runs, recoverable errors, tests without an LLM. TypeScript, MCP SDK v2, built with Claude Code.

Android emulator your AI agent drives on under half the RAM of Android Studio's (1.4 GB vs 3.5 GB): a text screen outline instead of screenshots, and per-device network, battery, location, screen, font and Android version. CLI + MCP server.

A self-healing scraper for hostile sites: broken selectors repair themselves, browser rendering kicks in when needed, and a coherent identity layer (Chrome TLS fingerprints, matched personas, vendor-aware Cloudflare/Akamai/DataDome handling) works to slip past bot detection. Ships with an MCP server so any LLM can drive a full crawl by conversation.