AI Workflows & Agentic Architecture Directory

Install Codebase Memory MCP to build a persistent knowledge graph of any codebase in milliseconds. 158 languages, 15 MCP tools, 99% fewer tokens. Single static C binary, zero dependencies, MIT license.

Parallax is a local-first AI orchestrator that pulls GitHub Issues, generates plans via Claude Code, requires human approval, and opens PRs. Full 2026 setup guide with CLI, dashboard, and Slack bot.

Bolt Foundry Gambit is an open-source typed-step verification framework for building trustworthy, inspectable AI agents with TDD-for-agents workflow, schema enforcement, trace evidence capture, and CI regression suites.

Deploy parallel AI coding agents with Codex Subagents for 5-7x faster PR review, batch file analysis, and CI/CD pipelines. Complete guide to built-in agents, custom TOML configs, and CSV batch processing.

mTarsier is the open-source MCP and skills manager that auto-detects Claude Desktop, Cursor, Windsurf, and VS Code Copilot. One dashboard, one CLI, one-click Marketplace installs.

Levent Alpöge used Claude Fable 5 to discover a counterexample to the Jacobian Conjecture (open since 1939). The C³ polynomial map has constant Jacobian -2 but maps three distinct points to the same output. Verified in L...

Complete guide to running 67B+ MoE models on consumer GPUs using KTransformers CPU-GPU heterogeneous inference with expert offloading.

Complete guide to building production-grade MCP servers with FastMCP 3.4 featuring remote proxy, OAuth, SSRF protection, and enterprise deployment on Prefect Horizon.

Complete guide to deploying AI agents across Slack, Telegram, WeChat, Discord, QQ, and Feishu from one codebase using AstrBot 35K-star framework.

OpenSEO is the first open-source SEO platform with native MCP server for AI agents. Complete guide to self-hosted keyword research, competitor analysis, and rank tracking.

BaseRT delivers 1.56x faster decode than llama.cpp and 1.35x faster than MLX on Apple Silicon. Complete benchmark comparison and setup guide.

Learn how Google Always-On Memory Agent on Gemini 3.1 Flash-Lite replaces chunking, embeddings, and vector databases with continuous LLM consolidation for zero-shot knowledge queries.