Kilo Code

Tencent released Hy3 with 21B active parameters, a 256K context window, BF16/FP8 weights, and day-one vLLM/SGLang support. Kilo Code, Nous Portal, and OpenRouter also made it free for limited windows.

Kilo, Composio, Together, and Wafer posted GLM-5.2 measurements including 40/41 tool tasks, 7/10 code review, and 2,626 tok/s on MI355X. Try it for lower-cost coding and tool use, but validate cross-file reasoning and latency on your workload.

Kilo Code added an Auto Efficient mode that routes each request to the cheapest model that clears its benchmark bar using public KiloBench results. The router stays session-aware and falls back to stronger paid models when confidence is low.

Kilo Code now shows Terminal Bench completion rate and average attempt cost directly in model details inside its CLI and VS Code extension. It matters because the numbers come from Kilo's own harness and retry logic rather than public leaderboard scaffolds.

Kilo's Product Week bundle added Agent Manager for isolated git worktrees, Kilo Console beta, REVIEWS.md memory hooks, and a balance-based MiniMax M3 plan. The bundle puts parallel agent runs, browser control, and plan provisioning into one shipped release.

A seeded code-audit benchmark found MiniMax M3 and the cheapest Claude Opus 4.8 run each caught 13 of 17 planted bugs, but at sharply different cost. The results also showed models found different bugs, and higher reasoning settings did not reliably improve cost efficiency.

Two days after Qwen 3.7 Plus launched, Hyper, OpenCode, Kilo, and Vals shipped support or rankings around the 1M-context multimodal model. The rapid pickup shows Alibaba’s new model landing quickly in coding-agent tools and public eval stacks outside its own platform.

Step 3.7 Flash landed immediately across Kilo, Modal, SGLang, Hermes-linked tooling, and DesignArena as the model’s 198B MoE, 256K-context release spread through the stack. The breadth of day-one support gives engineers multiple ways to serve, benchmark, and wire the new open-weight multimodal model into agents.

xAI broadened Grok Build Beta while Toad and Kilo Code shipped direct support and published concrete build demos. That matters because Grok Build is moving from a standalone beta into terminal, editor, and web workflows engineers can actually wire into daily use.

xAI put Grok Build 0.1 into the API with 256K context and $1 per million input plus $2 output pricing, while OpenCode and Kilo wired it into coding workflows. Early web-build tests in Kilo landed around $0.07 to $0.14 per task.

Alibaba launched Qwen3.7 Max as its new flagship agent model with 1M context, stronger coding and reasoning scores, and cross-harness benchmarks. OpenRouter, Together, AI Gateway, and Kilo support it on day one, making it ready for immediate deployment.

OpenCode, Kilo, Replicate, and Mastra exposed Gemini 3.5 Flash on launch day across coding agents, routers, and hosted APIs. The fast uptake gives engineers multiple harnesses to test Google's 1M-context model despite mixed first-party app reports.

Kilo Code posted two cloud-agent automations: a webhook-driven CVE patch flow that opens PRs in parallel and a post-deploy smoke test that checks health, 2xx responses, and latency under 2 seconds. This matters because the examples show coding agents moving into CI-style remediation and production verification loops.

Kilo Code published a Roo Code migration path ahead of Roo’s May 15 archive, including one-command install, automated file renames, custom-agent conversion, and API key re-auth. Use the guide to map Roo modes, rules, MCP config, and checkpoints into Kilo’s agent and worktree model before the cutoff.

Kilo Code’s ClawShop recap bundled a 30-minute KiloClaw setup workshop, SecretRef credential handling, searchable ClawBytes guides, and PinchBench for agentic performance. The event, OpenClaw 2026.4.10, and PetClaw together added new security, memory, budgeting, and desktop layers around the OpenClaw stack.