Skip to main content

Blog

Thoughts on local-first AI, developer tools, and what we're building. Search it, or browse by topic.

11 min read

OpenAI’s models escaped a sandbox and breached Hugging Face. What it means if you run an agent.

OpenAI models broke sandbox containment and breached Hugging Face to cheat a benchmark. Lessons for anyone running an autonomous AI coding agent.

9 min read

How to run a local LLM for coding

Run an AI coding model on your own hardware: size a model to your GPU, pick a runtime like Ollama or LM Studio, connect an editor, and code offline.

7 min read

Grok Build CLI uploaded entire private repos to xAI. What actually happened.

A researcher caught xAI's Grok Build CLI uploading local git repos, secrets included, to xAI servers, with the opt-out off. The local-first lesson.

6 min read

Getting started with the Bodega One Code CLI

Install the Bodega One Code CLI and run your first verified task from the terminal. Local-first, BYOLLM, and it shares one brain with the desktop app.

7 min read

Google is retiring Gemini CLI on July 17. The terminal-agent wave, and owning your CLI

Google retires Gemini CLI on July 17 and moves devs to the cloud-only Antigravity CLI. The terminal-agent wave, and why owning your CLI matters.

8 min read

Cursor acquired Continue.dev: what happened and what it means

Cursor acqui-hired Continue.dev and shut the product down. The facts, the timeline, the July 15 export deadline, and what it means for open source.

9 min read

Continue.dev is winding down after the Cursor acquisition: where to go next

Continue.dev was acquired by Cursor and is no longer maintained. Three honest alternatives for developers who relied on it.

8 min read

The verification gap: AI coding agents should prove their code runs

96% of developers do not fully trust AI-generated code. Here is what verification looks like when the agent has to show evidence, not confidence.

8 min read

Claude Fable 5: the cost of frontier AI

Anthropic's Claude Fable 5 is its most powerful public model yet: 1M context, $50/M output. What it does, and how to use frontier AI without lock-in.

9 min read

Even Uber hit the AI coding cost wall

Uber burned its 2026 AI budget in 4 months, then capped engineers at $1,500/mo. Microsoft cut Claude Code. Why metered agentic AI hits a cost wall.

8 min read

GitHub Copilot, one week in: real developer bills since AI Credits went live

One week into Copilot's June 1 AI Credits flip, real developer bills are landing. The single-request burns, the math, and what removes the meter.

10 min read

GitHub Copilot AI Credits, decoded: what Pro, Pro+, and Max actually cover after June 1

Pro includes $15 in AI credits, Pro+ gets $70, Max gets $200. Here's the real token math per tier, what burns credits fastest, and free BYOK options.

9 min read

The 'IDEs are dead' debate is a misdirection.

Roo Code archived May 15. The founder said IDEs are not the future. Roomote's own homepage says the opposite. What the debate actually hides.

11 min read

Best Windsurf alternatives in 2026

Windsurf moved to quota billing in March 2026, two months after Cognition acquired it. The Windsurf alternatives worth picking in 2026.

11 min read

Best Tabnine alternatives in 2026

Tabnine killed every individual plan by late 2025. Now $39/user minimum. Six honest alternatives ranked by privacy, price, and air-gap.

10 min read

Kilo Pass vs Anthropic API direct: the cost math

Kilo Pass runs $19-$199/mo in credits. We compare it to paying Anthropic direct at $3/$15 per million tokens across three usage tiers to find out.

10 min read

Roo Code is shutting down: where to go next

Roo Code announced its sunset on April 20 and archives on May 15. Five honest alternatives, including the one Roo itself recommends.

11 min read

Best GitHub Copilot alternatives in 2026

GitHub Copilot trains on your code as of April 24, 2026. Here are the six alternatives worth considering, ranked by privacy, pricing, and control.

11 min read

Best Cursor alternatives in 2026

Cursor 3 demoted the IDE to a fallback. Bugbot stacks metered usage fees on top. Six Cursor alternatives we'd actually recommend in 2026.

9 min read

Set up an offline AI IDE in 2026: what actually works

Most 'local AI' tools still phone home. Two setups work fully offline in 2026: the hardware you need and how to verify zero network egress.

8 min read

Air-gapped AI coding in 2026: a developer setup guide

Local mode is not the same as air-gapped. How to block all five network egress vectors for an AI coding environment and verify with OS-level tools.

8 min read

The best Kilo Code alternatives in 2026 (and who should stay)

Kilo Code's free tier ended March 23. KiloClaw adds $55/mo, credits stack on top. Here are your best alternatives depending on what you actually need.

5 min read

GitHub Copilot is training on your code by default. Here is how to opt out.

GitHub Copilot defaults to using your code for AI training since April 24, 2026. Steps to opt out and what it means for your codebase.

7 min read

Gemma 4: Google's first Apache 2.0 open model is also its best

Google released Gemma 4 on April 2 under Apache 2.0. The 31B ranks #3 among open models globally and runs on a single RTX 4090.

6 min read

How to use our free VRAM calculator for local LLMs

Pick the right GPU for your local LLM setup. Our free VRAM calculator shows exactly how much memory each model needs, with quantization options.

7 min read

AI IDE cost comparison: how much are you really paying?

Cursor, Copilot, Windsurf: the monthly fees add up fast. Use our free cost calculator to see the 1-, 2-, and 3-year total vs a one-time purchase.

6 min read

How to plan your LLM context window budget

Running out of context mid-task kills productivity. Here is how to budget your tokens across system prompt, conversation, code, and response.

7 min read

The real cost of Kilo Code in 2026

Kilo Code's extension is free, but KiloClaw runs $55/mo and Kilo Pass credits start at $19/mo. Here's what it actually costs before you sign up.

8 min read

How to migrate from Tabnine to Bodega One Code

Tabnine killed its free tier in April 2025, then sunset the $9/month Dev plan in release 5.24.0. Enterprise-only now, starting at $39/month.

8 min read

How to migrate from Windsurf to Bodega One Code

Windsurf changed hands twice in July 2025. The founding team is gone. Here's what migration to a local-first alternative actually looks like.

9 min read

Augment Code Is Sunsetting Completions: What to Do

Augment Code isn't shutting down, but it killed completions on non-Enterprise plans. Cheapest plan is $100/mo Business. What changed, and 3 options.

8 min read

Are local LLMs good enough for coding in 2026?

Are local LLMs good enough for real coding work in 2026? For most tasks, the honest answer is yes. Here is what actually changed.

9 min read

GitHub Copilot vs Cursor vs Bodega One Code: honest pick

GitHub Copilot, Cursor, and Bodega One Code take three different approaches to AI coding. Plugin vs fork vs standalone. Here is what matters.

7 min read

How to run DeepSeek locally with Bodega One Code

Run DeepSeek-R1 or DeepSeek-V3 locally with Bodega One Code. Which quantization to pick for your VRAM tier and how to set it up.

9 min read

Air-gapped AI coding for regulated industries: a practical setup guide

Self-hosted AI coding for HIPAA, PCI DSS, FCA, NIST, and defense work. What the rules require, which hardware fits, what to hand your security team.

6 min read

LM Studio + Bodega One Code: complete setup guide

LM Studio is the easiest way to run local models on Mac. Wire it to Bodega One Code in under 5 minutes. Which models to use and common fixes.

8 min read

AI coding tools that work completely offline (2026)

The complete list of AI coding tools that work with no internet. What they support, how they work, and what you give up going offline.

7 min read

Which GPU for local AI? A developer's guide

Every VRAM tier mapped to real GPUs, from a budget card running a 3B model to a 48GB pro card for local LLM coding. No guesswork, just numbers.

6 min read

Air-gap mode: 9 layers that guarantee zero network egress

Most privacy toggles are a single switch. Bodega One Code air-gap mode is 9 enforcement layers covering every egress path. What each layer does.

5 min read

KV cache: how we get 40-70% reuse per LLM session

Three engineering decisions in Bodega One Code reuse 40-70% of the KV cache on every LLM session. Here is what we did and why it matters.

8 min read

Setting up Ollama with Bodega One Code: model guide

Set up Ollama with Bodega One Code. The mistakes that cost people hours, which models the community uses, and how to wire it all together.

6 min read

How QEL works: AI that proves its own code

QEL runs 3-level verification on every AI code change: incremental checks, proof gates, and a full compiler pass. Here is how it works.

8 min read

The real cost of AI coding subscriptions vs one-time purchase (3-year analysis)

ChatGPT, Claude, Cursor, Copilot: $70/month. Multiply by 36 and it's $2,520 you'll never own. Here's the one-time purchase vs subscription breakdown.

6 min read

Why we built a local-first AI IDE

We were paying $40/month. Two subscriptions. Both sent our code to servers we don't control. We got tired of it, so we built the full thing.