Forkcast Weekly #3: codegraph, claude-plugins-official, Understand-Anything, openhuman

Episode Summary#

Four major projects dominate this week’s roundup: a code knowledge graph that gives agents semantic understanding of codebases, Anthropic’s official plugin ecosystem standardizing agent extensibility, a tool that transforms any codebase into an interactive Q&A knowledge graph, and the local-first OpenHuman AI assistant.

Repositories Covered#

codegraph#

A pre-indexed code knowledge graph for Claude Code, Codex, Cursor, and OpenCode. Provides local semantic indexing and graph traversal that dramatically reduces file scanning and tool calls across large multi-language codebases.

claude-plugins-official#

Anthropic’s official plugin registry for Claude Code. Standardizes plugin structure with three extension mechanisms — Skills, Commands, and MCP Servers — including 30+ first-party plugins for LSP support, PR review, and code quality.

Understand-Anything#

The #1 trending GitHub project that transforms any codebase into an interactive, searchable, Q&A-ready knowledge graph. Built with TypeScript, it integrates with every major AI coding agent and makes legacy code instantly understandable.

openhuman#

A local-first personal AI assistant with memory tree, Obsidian wiki integration, 118+ third-party integrations, and TokenJuice compression. Runs with Rust, React, and Tauri for a native desktop experience.

CLI-Anything#

Auto-generates command-line interfaces for any software, making it controllable by AI agents.

academic-research-skills#

Academic workflow skills for Claude Code

andrej-karpathy-skills#

A Claude Code plugin implementing four principles from Andrej Karpathy’s LLM coding observations: think before coding, simplicity first, surgical changes, and goal-driven execution. Forces the agent to state assumptions and define success criteria before writing code.

RuView#

A Rust-based code review tool that provides structured, automated review of pull requests with custom rule sets. Helps teams maintain code quality standards consistently across their codebase.

ai-engineering-from-scratch#

Learn it. Build it. Ship it for others.

skills#

A collection of production-grade engineering skills for AI coding agents by Matt Pocock. Provides structured, reusable capability files that make agents more reliable at TypeScript, testing, and general software engineering tasks.

superpowers#

An agentic skills framework and software development methodology that enforces TDD, spec-first workflows, git worktree isolation, and two-stage code review. With 200K+ stars, it defines how AI coding agents should work reliably across Claude Code, Codex, Cursor, and more.

scientific-agent-skills#

A collection of specialized AI agent skills for scientific research workflows. Covers literature review, citation graph analysis, peer review simulation, and methodology validation to accelerate academic and research processes.

chrome-devtools-mcp#

AI coding agents can write code but can’t see what happens in the browser — they’re blind to layout bugs, console errors, network failures, and performance issues 42+ tools across 10+ categories (input, navigation, debugging, performance, network, memory, extensions, emulation), built on Puppeteer, 47 releases, 829 commits, v0.25.0 (May 2026), integrates with 19+ MCP clients (Claude Code, Cursor, Copilot, Gemini CLI, Windsurf, etc.), Chrome 144+ for auto-connect, Node.js 20.19+, Apache 2.0

FinceptTerminal#

Finance terminal with market analytics and AI agents

supertonic#

Every TTS service is cloud-locked, expensive at scale, and fails on edge cases like financial expressions or phone numbers. You need TTS that runs offline and gets the details right. 31 languages in v3. ~99M parameters — much smaller than 0.7B-2B class open TTS systems. ONNX Runtime for cross-platform inference. Raspberry Pi demo at 0.3× RTF with zero network. Browser via onnxruntime-web (WebGPU/WASM). Handles financial expressions, phone numbers, technical units correctly where ElevenLabs, OpenAI, Gemini, and Microsoft TTS all fail. 11 inference runtimes: Python, Node.js, Browser, Java, C++, C#, Go, Swift, iOS, Rust, Flutter. Expressive tags: laugh, breath, sigh. MIT + OpenRAIL-M licensed.

llama.cpp#

LLM inference in C/C++

agentmemory#

A persistent memory system for AI coding agents that maintains context across sessions. Works with Claude Code, Codex, Cursor, and Copilot without client-specific dependencies.

oh-my-pi#

AI coding agent for the terminal

CloakBrowser#

Every web scraper eventually hits Cloudflare, reCAPTCHA, or fingerprinting. Stock Playwright scores 0.1 on reCAPTCHA v3 — instantly flagged as a bot. 57 C++ source-level fingerprint patches (not JS injection). reCAPTCHA v3 score: 0.9 (human-level) vs Playwright’s 0.1. Cloudflare Turnstile: PASS. FingerprintJS: PASS. BrowserScan: NORMAL (4/4 checks). bot.incolumitas.com: 1 fail vs Playwright’s 13 fails. 30+ detection sites tested. navigator.webdriver: false (source-level patch). Humanize mode: Bezier mouse curves, per-character typing delays, realistic scroll acceleration. ~190MB RAM idle, ~280MB with 3 tabs. Drop-in Playwright replacement. Cross-platform: Linux, macOS, Windows. MIT wrapper + proprietary binary.

OpenWA#

Free self-hosted WhatsApp API Gateway

odoo#

Open source ERP suite

rtk#

CLI proxy reducing LLM token consumption 60-90%

agency-agents#

Generic ‘act as a developer’ prompts produce mediocre output — production work needs specialized AI agents with personality, proven processes, and domain expertise. 144+ specialized agents across 12 divisions (Engineering, Design, Paid Media, Sales, Marketing), 10,000+ lines of content, 11 tool integrations (Claude Code, Copilot, Cursor, Gemini CLI, Aider, Windsurf), multi-agent example deploys 8 agents simultaneously.

Anthropic-Cybersecurity-Skills#

Security teams lack structured, framework-mapped skill files that AI coding agents can use to perform consistent security assessments across different tools. 754 structured cybersecurity skills. Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF. agentskills.io standard. Compatible with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini.

agent-skills#

A production-grade engineering skills library for AI coding agents by Addy Osmani. Standardizes engineering practices and quality gates to make agents more professional and reliable across various development workflows.

cfnew#

Cloudflare Workers multi-protocol proxy

the-book-of-secret-knowledge#

Collection of lists, manuals, cheatsheets, hacks

presenton#

Open-source AI presentation generator

notebooklm-py#

Unofficial Python API for Google NotebookLM

Shadowbroker#

Aggregates open-source intelligence from 60+ live feeds into a single map interface with AI agent correlation.

multica#

Open-source managed agents platform

12-factor-agents#

12 principles for production-grade LLM agents

streambert#

Cross-platform Electron app for streaming movies/TV/anime

Sana#

Efficient high-resolution image synthesis

forge#

Guardrails that take an 8B parameter model from 53% to 99% accuracy on agentic tasks. Implements structured output validation, tool-use constraints, and safety filters that dramatically improve small model reliability for autonomous agent workflows.

Watch#

• Video: https://www.youtube.com/watch?v=Z0Csq15WFvo
• Cover: https://i.ytimg.com/vi/Z0Csq15WFvo/hqdefault.jpg

Notes#

Transcript and notes will be added from Forkcast output artifacts.