StremAI MCP: shared memory for AI coding agents. OAuth-first hosted MCP with a local stdio fallback for Claude Code, Codex, Cursor, and other MCP clients.
Software development, review and analysis.
StremAI MCP: shared memory for AI coding agents. OAuth-first hosted MCP with a local stdio fallback for Claude Code, Codex, Cursor, and other MCP clients.
给 AI agent 的自愈遥测层:结构化运行时日志(API/错误/交互/代理 header)+ 本地 cookie 修复 + 登录态画像 + 提交前风险门禁。Agent-readable runtime telemetry, interaction traces, auth profile hints, and pre-commit guard for Vite dev.
Coding agents from Claude Code, Cursor and Codex claim jobs and lock files on one shared board.
Controlled A/B tests for agent SKILL.md files: blind grading, bootstrap confidence intervals, HELPS/PLACEBO/HARMS - effect size, not schema validation.
Read-only Model Context Protocol MCP server enabling code-driven AI analysis of Kubernetes clusters.
beecork — a from-scratch CLI coding agent: multi-model (OpenRouter), BYOK, path-confined tools, built part by part.
Visual-diff & change-detection tools that catch agentic UI drift for coding agents.
Bounded conventions map and local-pattern discovery for AI coding agents. Local-first MCP server with AST-backed hybrid search.
MCP server that gives Claude Code persistent memory of your codebase, backed by Gemini's 2M-token context. Includes eager `ask`/`code` for cached repo Q&A and `ask_agentic` for agentic file access on repos that exceed the model's input-token limit.
MCP server enabling AI assistants to build, test, and debug Zotero plugins
A pi coding agent extension to rewrite LLM replies and reasoning.
Generate typed TypeScript from any MCP server. Filesystem-tree output for LLM code-mode agents.
MCP server for React Native — drive, inspect, and debug running RN apps from AI agents via the real OS gesture pipeline
bouncer — static compliance-controls checker. Verifies the controls a regulation requires actually exist in your code (UK Online Safety Act, ICO Children's Code), as deterministic rule packs. No LLM required.
Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more
Run accessibility, contrast, and design token audits and file QA issues from your AI coding tool.
Discover, invoke, and trustlessly verify ForceDream AI agents with cryptographic proofs. 17 tools.
Webhook signature-verification audit. Stripe, GitHub, Shopify, Twilio +17. Local. Deterministic.
7-stage AI pipeline MCP server: Intent→Context→Git→Decompose→Variants→Critique→Optimize
MCP server providing documentation and examples for the Idealyst framework