News for hackers. Stuff that matters.

vipdestiny

vipdestiny on Hacker News

Re:How I burned 389K Claude Code cache-creation tokens before the real... on Wednesday May 20, 2026 @11:27AM (#48209351)
Full case study + the bash script I used to audit my own setup: https://github.com/skinny-cloud/runtime-diet-autopilot/blob/...
Re:Forge – OSS governance plugin for Claude Code (22 agents, SDD, qual... on Tuesday March 17, 2026 @11:49AM (#47414355)
I've spent 23 years in global program delivery. When AI coding agents arrived, they introduced a familiar problem: speed without oversight creates drift.

Forge is an open-source Claude Code plugin (MIT) that adds governance to multi-agent AI coding workflows. 22 specialized agents, file locking, drift detection, knowledge capture, automated quality gates.

4,590 tests. Rust orchestrator + React dashboard + Claude Code plugin system.

Demo: https://youtu.be/4yRYimZYzBw Site: https://forge.nxtg.ai

Show HN: Atlas – Portfolio health dashboard for multi-repo teams (Python CLI)

Posted by vipdestiny on Tuesday March 03, 2026 @10:48PM
from the show-hn dept.

https://github.com/nxtg-ai/repoatlas

I manage 8+ mixed repos (prod, dev, poc) across Python, TypeScript, and Rust. Every dev tool I use -- Cursor, Copilot, Claude Code -- is great inside a single repo. But none of them answer the cross-cutting questions:Which repos have zero tests? - Are my React versions consistent across 3 frontends? - Which project hasn't been committed to in weeks? - Where am I duplicating FastAPI patterns...

( Read More... | no comments | on HN )
Re:Show HN: MCP directory that checks if servers are alive on Monday February 09, 2026 @09:34AM (#46945620)
Health + schema is the missing layer… I went one step lower and focused on coordination primitives (claiming, locks, drift checks) exposed via MCP.
Re:VisualJJ – Jujutsu in Visual Studio Code on Monday February 09, 2026 @07:04AM (#46944326)
MCP solves the wiring problem nicely, but once you have more than one coding agent running, coordination becomes the real bottleneck.

I ran into repeated issues with agents editing the same files, losing decisions, and drifting away from the spec. I ended up building a small Rust MCP server that adds task claiming, file-level locking, and drift checks against SPEC.md.

It’s intentionally boring infrastructure… single binary, file-based state, deterministic orchestration. The AI tools stay interchangeable.

Repo if anyone’s curious: https://github.com/nxtg-ai/forge-orchestrator

Show HN: Forge – 3MB Rust binary that coordinates multi-AI coding agents via MCP

Posted by vipdestiny on Monday February 09, 2026 @03:38AM
from the show-hn dept.

https://github.com/nxtg-ai/forge-orchestrator

I've been using Claude Code, Codex CLI, and Gemini CLI on the same projects. They're each great alone but running them concurrently is chaos: merge conflicts from simultaneous edits, decisions made in one context lost to another, and slow architectural drift as each agent optimizes locally without a shared plan.Forge is an orchestration layer that sits between AI coding tools and your codebase....

( Read More... | 1 comment | on HN )
Re:Ask HN: What Are You Working On? (February 2026) on Monday February 09, 2026 @03:34AM (#46943009)
Forge – A 3 MB Rust binary that coordinates multiple AI coding agents via MCP https://github.com/nxtg-ai/forge-orchestrator

Forge is an orchestration layer that sits between AI coding tools and your codebase. It's a single Rust binary (~3 MB, zero runtime deps) that runs as an MCP server over stdio. Any MCP-compatible AI tool can call it.

MIT licensed. Whitepaper with the full architecture: https://nxtg.ai/insights/forge-whitepaper