Kilo is an open-source all-in-one agentic platform. 3M+ Kilo Coders. 500+ models. No markup.https://bsky.app/profile/kilocode.aihttps://bsky.app/profile/kilocode.ai/post/3mrqd75vp2h2xWe keep arriving at the same conclusion in these experiments: you don't need the most expensive model for every step of your workflow. So we tested whether Kilo Code's Auto Model router could act on that better than picking models by hand.28 Jul 2026 21:12 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mrqd75vp2h2xhttps://bsky.app/profile/kilocode.ai/post/3mrcvsfdkv325More ways to control your AI coding spend are live: 📊 Cost Insights: what's driving your cost, broken down by product & user 🔔 Spend Alerts: get notified about unusual usage spikes 💡 Cost Suggestions: inference suggestions based on usage Read more: blog.kilo.ai/more-ways-to-control-ai-coding-spend23 Jul 2026 13:07 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mrcvsfdkv325https://bsky.app/profile/kilocode.ai/post/3mr6pwqcmts2rEveryone's waiting for a second "DeepSeek moment." We don't think it's coming. Open models like Kimi K3 top the intelligence charts, but serving them made throughput fall off a cliff. The scarce thing was never the model, but the compute to run it. Read more: https://blog.kilo.ai/p/no-second-deekseek-moment21 Jul 2026 21:12 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mr6pwqcmts2rhttps://bsky.app/profile/kilocode.ai/post/3mqccf7cgzm2wKilo Code is now available for JetBrains IDEs as a native Kotlin/Swing plugin built on the IntelliJ Platform. It includes chat, slash commands, file mentions, MCP servers, and model selection. Available now on the JetBrains Marketplace. https://blog.kilo.ai/p/kilo-code-goes-native-on-jetbrains10 Jul 2026 13:55 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mqccf7cgzm2whttps://bsky.app/profile/kilocode.ai/post/3mq5inx2y7f2yThe AI race isn't heating up. It's on fire. Pricing changes. Models getting pulled out from under your feet with no warning. And now Palantir's CEO went on CNBC to call the whole thing "effing insane."08 Jul 2026 16:03 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mq5inx2y7f2yhttps://bsky.app/profile/kilocode.ai/post/3mphtsv6ve42iAuto Efficient is a next-generation model router inside Kilo. It's session-aware and informed by real benchmark data. On average, it's 77% cheaper than Claude Opus 4.8 while retaining nearly 70% performance parity. Check out the numbers here: https://kilo.ai/auto-efficient-vs-opus30 Jun 2026 01:25 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mphtsv6ve42ihttps://bsky.app/profile/kilocode.ai/post/3mozwnwpgoc2v10 months ago we predicted AI coding bills would hit $100k/dev/yr. This week Ramp confirmed ~$90k. The fix isn't capping usage or downgrading everyone. It's routing each task to the model that fits it. Kilo's Auto Model does it by default. kilo.codes/0c9ftEx https://kilo.codes/0c9ftEx24 Jun 2026 12:38 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mozwnwpgoc2vhttps://bsky.app/profile/kilocode.ai/post/3moy5tykyct2rStop paying frontier prices to rename a variable! Auto Efficient routes each request to the cheapest model that can handle it, picked on a public benchmark you can check. Easy tasks run lean, hard ones stay reliable. Live now: kilo.codes/0c9ftEx23 Jun 2026 19:42 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3moy5tykyct2rhttps://bsky.app/profile/kilocode.ai/post/3mouzoamdnt2rAugment is sunsetting its JetBrains IDE extensions, w/ ~a month of notice. The alternatives: a CLI or an enterprise platform. Kilo's plugin already covers what PyCharm and IntelliJ devs want: native v7, Apache-2.0, 500+ models, no $100 floor. blog.kilo.ai/p/is-augment-sunsetting-its-ide-extensions22 Jun 2026 13:49 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mouzoamdnt2rhttps://bsky.app/profile/kilocode.ai/post/3monk4j5res2rKilo now shows benchmark data right in the model picker, CLI and VS Code. Each model lists its Terminal Bench completion score and average cost per attempt, measured in Kilo's own harness. GPT-5.5 completes 74.1% of tasks, Kimi K2.6 hits 54.4%. Full table: kilo.ai/leaderboard https://kilo.ai/leaderboard19 Jun 2026 14:22 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3monk4j5res2rhttps://bsky.app/profile/kilocode.ai/post/3mokl6c3z6c2rWe ran GLM-5.2 and Kimi K2.7 Code through the same test: plan a feature flag service, then build it. GLM's plan scored 9.0 to Kimi's 8.1. But once both built from GLM's plan, the services were near identical. The planner matters more than the builder now. https://blog.kilo.ai/p/glm-52-vs-kimi-k27-code-which-model18 Jun 2026 10:03 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mokl6c3z6c2rhttps://bsky.app/profile/kilocode.ai/post/3moikh227tc27Inceptron is live in the Kilo Gateway. Sovereign, EU-hosted inference without giving up model choice. Kimi K2.6, GLM 5.1, MiniMax M2.5. GDPR and ISO 27001 compliant. From $0.15/1M input tokens on MiniMax M2.5. https://blog.kilo.ai/p/kilo-partners-with-inceptron-for17 Jun 2026 14:44 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3moikh227tc27https://bsky.app/profile/kilocode.ai/post/3moi6zzn3ls2h$15 on Opus. $1.70 on the same task with a cheaper model. Most of what an agent does all day doesn't need a frontier model, you're just paying like it does. Here's how to cut your AI bill: https://blog.kilo.ai/p/4-spend-levers17 Jun 2026 11:20 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3moi6zzn3ls2hhttps://bsky.app/profile/kilocode.ai/post/3mogaxlzpvs27SpaceX is buying Cursor for $60 billion. SpaceX has the compute, Cursor has the distribution into half the Fortune 500, and the base models are converging. Once a tool gets acquired, its model choices serve the acquirer, not you. https://blog.kilo.ai/p/spacex-just-bought-cursor-for-6016 Jun 2026 16:49 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mogaxlzpvs27https://bsky.app/profile/kilocode.ai/post/3mofh4q7hhk27Fable 5 and Mythos 5 got pulled 3 days after launch over a US export directive. The frontier didn't go with them. GPT-5.5 tops KiloBench, Nemotron 3 Ultra is free and self-hostable, MiniMax M3 runs ~1/40th Fable's cost. The frontier is wider than one lab. https://blog.kilo.ai/p/you-dont-have-to-use-fable-and-mythos16 Jun 2026 09:07 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mofh4q7hhk27https://bsky.app/profile/kilocode.ai/post/3moe2rikep227Better than Fable 5, better than Le Chaton Fat, and better than whatever you're switching to tomorrow. Multiple models beats one single model. Every time.15 Jun 2026 19:53 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3moe2rikep227https://bsky.app/profile/kilocode.ai/post/3modwxrwwl227The group chat will no longer be the one telling you your team lost. World Cup ClawByte, one-click install in KiloClaw, daily summaries + get yesterday's scores in your time zone, all piped to Telegram.15 Jun 2026 18:45 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3modwxrwwl227https://bsky.app/profile/kilocode.ai/post/3modfxfrrhc27Dad what was it like when we had access to Fable?15 Jun 2026 13:41 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3modfxfrrhc27https://bsky.app/profile/kilocode.ai/post/3mo6n6femth2dICYMI: Product Week shipped five things this week. All of them, in one place 🧵13 Jun 2026 16:07 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mo6n6femth2dhttps://bsky.app/profile/kilocode.ai/post/3mo4x5hzc652dMost AI review tools run the same generic rubric on every repo and miss what your team actually cares about. Code Reviews now adapt: drop a REVIEWS.md in your repo and the agent enforces your conventions, not someone's default. Live now.13 Jun 2026 00:00 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mo4x5hzc652dhttps://bsky.app/profile/kilocode.ai/post/3mo4agyc5kc27Two new coding models and a sold-out token plan this week in Kilo. Kimi K2.7 Code from Moonshot, Claude Fable 5 topping our coding benchmarks, and the MiniMax token plans selling out fast enough to need a new batch already.12 Jun 2026 17:13 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mo4agyc5kc27https://bsky.app/profile/kilocode.ai/post/3mo2igxop6z26The Kilo CLI now has a face. Kilo Console is a local, browser-based UI for managing your projects, git worktrees, sessions, and settings. No more hand-editing JSON. Now in beta.12 Jun 2026 00:31 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mo2igxop6z26https://bsky.app/profile/kilocode.ai/post/3mnzqmn42v227"Open doesn't just mean weights." Chris Alexiuk of NVIDIA on everything the Nemotron family opens up: the data, the recipes, the technical report. The whole point is an open science community around models.11 Jun 2026 17:25 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mnzqmn42v227https://bsky.app/profile/kilocode.ai/post/3mnzdqmk2p22tA secret got committed to Git, then "erased" with a branch rewind. The repo looked clean. We ran Grok Build 0.1 on this Terminal-Bench task. It found the orphaned commit, saved the secret, and actually scrubbed the history. 27 steps, 41 seconds, $0.09. Writeup: https://blog.kilo.ai/p/we-asked-grok-build-01-to-recover11 Jun 2026 13:34 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mnzdqmk2p22thttps://bsky.app/profile/kilocode.ai/post/3mnxwaxayd32eMiniMax M3 benches near Claude Opus 4.8 at a tenth of the price. Coding Plans are live in Kilo. Buy them with the balance you already have, no separate subscription.11 Jun 2026 00:00 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mnxwaxayd32ehttps://bsky.app/profile/kilocode.ai/post/3mnx2lasv5c2tOn June 1, GitHub Copilot switched to token-based billing. Developers are reporting bills 10x higher, with some burning through a month of credits in hours. Meanwhile, a quieter shift has been underway. There's something for switchers at the end of this thread. 🧵10 Jun 2026 15:45 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mnx2lasv5c2thttps://bsky.app/profile/kilocode.ai/post/3mnvg6sj55c2pThe dentist appointment you forgot. The standup it knew you'd miss. The Telegram ping to fix it. This is KiloClaw now. 🦞10 Jun 2026 00:08 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mnvg6sj55c2phttps://bsky.app/profile/kilocode.ai/post/3mnunfnsots2tHit by the June 1 Copilot billing change? Bring your ChatGPT Plus or Pro subscription into Kilo and run GPT-5.5 at a flat rate, in your IDE or CLI. https://kilo.ai/use-chatgpt-subscription-in-kilo09 Jun 2026 16:44 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mnunfnsots2thttps://bsky.app/profile/kilocode.ai/post/3mnsvgwju7t2sSame prompt, three models, three answers. You keep the one you like. Agent Manager is live in Kilo Code. Every agent runs in its own git worktree, so they work in parallel without touching each other's files.09 Jun 2026 00:03 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mnsvgwju7t2shttps://bsky.app/profile/kilocode.ai/post/3mnsdmnw64s2t3 points higher on the benchmark. 8x more expensive to actually run. Guess which one was the right model to ship? Benchmarks tell you who wins. They don't tell you what it costs to win. KiloBench does. https://blog.kilo.ai/p/kilobench-because-your-benchmark08 Jun 2026 18:44 +0000at://did:plc:3ql4fo6phig6w7andme7ug72/app.bsky.feed.post/3mnsdmnw64s2t