Provides a local, vendor-agnostic control room where coding agents can be assigned tasks, exchange scoped messages, submit claims, and have work reviewed across different models, with a voxel-world interface for inspecting sessions and evidence.
Provides AI coding agents with five intelligence layers (dependency graph, git history, documentation, architectural decisions, code health) via nine MCP tools, enabling deep codebase understanding and reducing exploration cost.
Enables Claude Code to start and continue Codex tasks through MCP tools, preserving sessions and reporting runtime health. Includes CLI compatibility checks and a pinned runtime fallback for Codex updates.
Governed memory for coding agents with trust lifecycle, conflict detection, staleness tracking, and health scoring. SQLite + FTS5, zero infrastructure. Works with Claude Code, Cursor, Codex, Windsurf.
Advanced MCP server for Godot 4.6+ with 63 professional tools, enabling AI-assisted game development with backup/rollback, deep script validation, and project health diagnostics.
MCP server that enables an agent to autonomously build, compile-check, test, and debug DayZ mods, integrating with the running game via a server bridge and providing structured verdicts, world manipulation, client control, and API knowledge indexing.
Enables any MCP client to hand self-contained coding tasks to a local DeepSeek Harness instance, which executes them by reading and editing files and running commands within whitelisted directories. Exposes a health check and a blocking task-runner over stdio or authenticated HTTP, returning stdout, stderr, exit code, and duration.
An autonomous multi-agent orchestration layer that generates a bespoke software engineering organization for a given objective, runs parallel OpenCode workers in isolated git worktrees, and integrates reviewed code through a replan loop.
Enables unified access to a multi-node DSH control plane, routing ChatGPT tool calls to appropriate node agents with presence awareness, health monitoring, and fail-closed execution.
Empower any MCP-compatible AI Agent(MCP Client) with engineering-grade capabilities to understand, modify, run, and deliver real-world code repositories.
AI-native open-source 2D game engine whose MCP server exposes every editor operation to coding agents as typed commands, so an agent can build, run, and verify a game inside the editor. It runs locally on macOS, Windows, and Linux with no cloud service or API key.
Enables AI coding providers to run structured multi-agent workflows with tracked documents, task claims, action logs, handoffs, and server-owned health evidence.
Enables users working inside Claude or ChatGPT to build software end to end, executing every command, test, and health check in an isolated cloud sandbox so progress is blocked unless each step is proven by real output, and finishing with a live public preview URL. It also lets sessions checkpoint and restore risky fixes, with access unlocked by a Stripe Checkout purchase.
Enables MCP clients like Claude Code to delegate coding tasks to a local model through a configurable coding-agent CLI backed by any OpenAI-compatible endpoint, with tools for health checks, task execution, and context-aware file modifications.
Lets any MCP-capable coding harness (Cursor, Claude Code, Codex, Gemini CLI, VS Code/Copilot, opencode, and others) hand a self-contained task to a real, isolated DeepSeek Harness process that works in a chosen workspace with its own context window, model, and toolchain, then returns the final answer. Exposes task submission with time estimates and acceptance criteria, status polling with live progress and process-tree telemetry, graceful cancel and forced kill of whole process trees, and a health probe reporting concurrency, deadlines, and recent jobs.
Enables querying DeepSeek-Flash with configurable chain-of-thought effort and running autonomous code tasks that plan a spec, edit files, run tests, and self-review the resulting diff. Also provides adversarial code auditing, API health and latency checks, plus workspace, command-blacklist, and Git branch safety guardrails.
Exposes tools that scan a repository for dependency bloat and fragile patterns, return a scored codebase health report, validate proposed code and bash commands before execution, and suggest drop-in native standard library replacements for bloated packages. It also injects intensity-specific system instructions into the client, enabling agents to write leaner, dependency-free, production-hardened code.
Enables MCP clients and local orchestrators to drive Codex Desktop and codex-app-server as a durable async worker: submit tasks or Plan Mode workflows, immediately receive an operation or workflow ID, and poll for status, approvals, and final reports instead of holding long blocking calls. It adds retry-safe request IDs, duplicate-turn protection, SQLite-persisted state with leases and heartbeats for restart recovery, plus health checks, diagnostics, and repair tools.