Posts

T3MP3ST turns Claude Code or Codex into an autonomous red-teaming framework — benchmarked at 90.1% on XBEN. Here’s my hands-on test.

Ever sat through an AI agent generating 15,000 lines of code in one shot, only to stare at a diff so massive you just say “looks fine” and merge blind? Yeah, me too. And that’s exactly the problem Backlog.md solves. I’ve been testing it for the past hour on a Ryzen 9 workstation, and honestly? This isn’t another Kanban tool. It’s an attention fragmenter for the AI coding era — and the 5,900 GitHub stars make more sense the longer you use it. ...

Ever asked an AI agent to write a Python script, then hesitated because you had no idea what pip install might pull in? Yeah, me too. AI agents are fantastic at generating code. Still, trusting them to execute it on your machine? I’ve debugged enough MCP tool calls to know better. That’s exactly why I went looking for E2B (12.8k ★ on GitHub) — an open-source sandbox that runs AI-generated code inside Firecracker microVMs. Not Docker containers. Not WASM runtimes. Actual microVMs, each with its own kernel, memory, and network stack, booting in under 200ms. ...

Ever opened your Claude Code or Cursor bill and thought, “I know I spent this much, but I have zero idea on what”? Yeah, same here. Month after month, a single number — $X,XXX.XX — with zero breakdown. Which model burned the most? Which project ran up the bill? That dumb conversation I left running overnight? CodeBurn (8,428 ★, MIT) is a local-first CLI that reads your existing session files and breaks down every token and dollar by task, model, tool, and project across 31 AI coding tools. And it runs with a single command — no install, no config, no data leaving your machine. ...

So you spend an hour wiring up an MCP server. Your Claude Code client connects fine — no errors. But when you ask it to use a tool, nothing happens. Or worse, it calls the tool with arguments that look weird, and you have no idea why. That’s the blind spot. The MCP Inspector is a standalone test client — it can’t see what your real client is actually sending. You’re debugging in the dark. ...

Eight terminal windows. That’s what I counted on my desktop this morning — three of them running different AI coding agents alone. OpenCode in one tab, Goose in another, Hermes Dashboard eating up a browser window. Every swap meant alt-tabbing through a maze. So when I stumbled on Junction — a VS Code extension that puts all 7 local agent backends into one sidebar panel — I was sold. Setup took about 30 seconds. ...

Ever had your Claude Code produce a killer analysis, scroll past it three messages later, and realize you can’t find it again without dumping the whole terminal history? Yeah, me too. I’ve been running coding agents for months now — OpenCode, Claude Code, Goose — and the single biggest pain point isn’t the quality of their work. It’s that their work lives in a chat scrollback that evaporates the second your session ends. ...

Ever watched a single AI agent spin in circles on a complex problem? I have. Claude Code will happily burn 20 minutes exploring a dead end with no way to pull itself out. That’s the exact problem Muteki was built to solve. Muteki (無敵, “Invincible”) is an open-source multi-agent swarm — 217★ on GitHub and growing fast — that orchestrates Claude Code, Codex, and Cursor as a coordinated team. So instead of one agent talking to itself, it dispatches different agents to different sub-problems, shares findings through a shared blackboard, and keeps the whole operation moving toward the goal. And it’s not theoretical — it placed 8th at RIFFHACK 2026 with zero human intervention and scored 200/200 on the NYU CTF benchmark. ...

Your primary AI provider goes down, and your entire coding pipeline just stops. No fallback. No graceful degradation. Just a dead session. That’s the exact pain that drove me to test OmniRoute — a free, self-hosted AI gateway with 236 providers, stacked token compression, and a fallback system that actually works. And at 9,770 GitHub stars (climbing 1,010 per day as of writing), I’m not the only one watching this project. ...

Ever spent half a session re-teaching your AI agent how to reach the prod DB, where the credentials live, and the exact deploy command — only to have it forget everything the moment you close the terminal? Yeah, me too. I’ve been running Claude Code and Cursor daily for months now. And the single biggest frustration isn’t the code quality. It’s that every session starts from zero. The hard-won knowledge from debugging that flaky CI job or discovering the one weird config quirk that breaks staging — poof, gone when the session ends. ...