发现了一个对于 Harness 开发者似乎很有用的网站 phistory.cc/ 里面有 Claude Code、OpenCode、Codex、Pi、OpenClaw、Hermes 等各种 Harness 的各个版本的 system prompt 以及 tool schema。 Tip: 点击右上角“Trace”是看上去比较舒服的另一个视图。

OpenCodeのKimi 2.7、Claude CodeのOpusくらいのポンコツさだから確かにOpusくらいの性能あるのかもしれない

さくらのAI EngineのKimi K2.6、OpenCodeだと画像の入力ができなかったんだけど opencode.jsonc にmodalitiesとか言う項目追加したらいけるようになった

⚡️Xiaomi has launched MiMo Code (4.3k⭐) It is an open-source coding agent built on top of OpenCode. The package includes MiMo Auto, a temporarily free mode on MiMo-V2.5 with up to a 1M-token context. You can also sign in via Xiaomi MiMo, import a Claude Code config, or connect other providers. What’s interesting: ▫️ Max Mode At each step, the agent creates 5 independent drafts: reasoning tool-call plan, without execution. Then a judge selects the best option, and only that one gets executed. Xiaomi reports 10–20% on SWE-Bench Pro, at the cost of roughly 4–5x more tokens. The feature is experimental. ▫️ Goal /goal defines the stopping condition. Before finishing, a separate judge checks whether the task has actually been completed. ▫️ Memory Memory is handled by a dedicated checkpoint-writer. It writes checkpoint. md, promotes stable facts into MEMORY. md, stores the full trace in SQLite, and parses notes. md, where the main agent can drop findings. When the context fills up, the session is rebuilt from the todo list, checkpoint, latest user messages, and memory. That is their version of “unlimited context.” ▫️ Compose A separate mode next to build/plan. Essentially, it is a built-in flow in the style of Superpowers skills. The Compose agent runs the task through skills like compose:brainstorm, compose:plan, compose:tdd, compose:execute, compose:review, compose:verify, and compose:merge. It is like specs-driven development: from spec to implementation, checks, and merge. In other words, they baked the development process right into the harness - respect for that. ▫️ Dynamic Workflow For large tasks, there is JS orchestration: agent(), parallel(), pipeline(), workflow(). Parallel subagents and process logic live in an executable scenario, so complex flows depend less on whether the model can keep the order of steps in its head. ▫️ Dream / Distill Dream cleans and merges project memory every 7 days. Distill looks for recurring processes every 30 days and turns them into skills, commands, agents, and SOPs. This looks like one of the most interesting new coding agents: Xiaomi has built an agentic system for long-running tasks with memory, completion verification, an SDD-style development mode, and parallel orchestration. One nuance: you will not see the GPT-5.5 model right away, because they use a plugin for ChatGPT OAuth that does not include this model. But MiMo GPT-5.4 itself managed to make a patch, after which the model became available.

Almost out of #opencode jail. Here's $5 on me while we wait : opencode.ai/go?ref=08M7YCN5J… @opencode

Your coding agent can now generate Excalidraw diagrams that "argue visually" — not just boxes and arrows. This new skill for Claude Code / OpenCode agents turns natural language descriptions into proper architectural diagrams with visual validation built in. What makes it different from every other "diagram from text" tool: - Semantic shapes: fan-outs for one-to-many, timelines for sequences, convergence for aggregation. No uniform card grids. - Evidence artifacts: technical diagrams include real code snippets and actual JSON payloads embedded in the shapes. - Visual validation loop: a Playwright-based render pipeline lets the agent see its own output, catch layout issues (overlapping text, misaligned arrows), and fix them in a loop before delivering. - Brand-customizable: all colors in one file. Swap the palette and every diagram follows your brand. The workflow: drop the skill into `.claude/skills/`, ask your agent "Create an Excalidraw diagram showing how X works", and it handles the rest — concept mapping, layout, JSON generation, rendering, visual validation. This is a great example of the skill system done right. Instead of building a standalone tool, it extends the agent's capabilities at the skill layer. Install it, tell the agent what you want, and let it iterate. github.com/coleam00/excalidr…

OpenCode v1.17.6 new update : • Improved MCP server compatibility by declaring OpenCode's supported client capabilities. npm install -g @anomaly/opencode github.com/anomalyco/opencod…

Kimi K2.7 Codeいいな。体感でDeepSeek V4 Proよりも賢くGPT-5.4くらいに感じる。そしてGPT-5.4よりも日本語が丁寧。OpenCode Kimi K2.7 Codeに実装計画を立てさせてCopilot CLI GPT-5.4にコーディングをさせている(年間プランでまだプレミアムリクエストが使えるので)

There's a repo that makes your AI agent write 80 to 94 percent less code, and the whole idea is a joke about a guy you have already met. DietrichGebert/ponytail. About 1,700 stars in two days. It drops the laziest senior dev in the company inside your coding agent. The one with the ponytail and the oval glasses who has been there longer than the version control. You show him fifty lines. He says nothing and replaces them with one. Here is how it actually works. Before the agent writes anything, it walks down a ladder and takes the first rung that holds: 1. Does this need to exist at all? If no, skip it. 2. Does the standard library do it? Use that. 3. Native platform feature? Use that. 4. Already-installed dependency? Use that. 5. Can it be one line? Make it one line. 6. Only then, write the minimum that works. The example that sells it: you ask for a date picker. A normal agent installs flatpickr, writes a wrapper component, adds a stylesheet, and starts a discussion about timezones. Ponytail writes one plain input with type date. The browser already had one. Lazy, not negligent. It never touches input validation, data-loss handling, security, or accessibility. And every shortcut leaves a ponytail comment in the code naming its upgrade path, so the cuts are auditable, not silent. The numbers are the project's own benchmark, but they are reproducible: five everyday tasks, three models, Haiku, Sonnet and Opus, median of ten runs each. 80 to 94 percent less code, 47 to 77 percent cheaper, 3 to 6 times faster than the same agent with no skill. You can rerun the whole thing yourself with promptfoo. How to use it. In Claude Code it is two lines: /plugin marketplace add DietrichGebert/ponytail /plugin install ponytail@ponytail That is the entire setup. It runs every session. /ponytail-review scans your current diff for what to delete. /ponytail ultra is for when the codebase has wronged you personally. Modes go lite, full, ultra, off. It works across about ten agents. Codex, Cursor, Windsurf, Cline, Copilot, Aider, Kiro, OpenCode, Pi. You either install the plugin or copy the one matching rules file for your tool. MIT licensed. It is the cleanest YAGNI I have seen shipped as a tool. The best code is the code you never wrote. github.com/DietrichGebert/po…

Ollama Cloud 早期不穩定常常斷線，目前還不錯可以嘗試下 - 雲額度比 OpenCode Go 多，但是如果只是純用在 coding 的話，總體價值感覺還是 OpenCode Go 比較值得些... 如果要改變 Codex 底座模型著不一樣，Ollama Cloud 挺值得

I just realized. You can connect and use OpenRouter in OpenCode without subscribing to Go

Ahoy fam Name's one openCode with mesource bug hunter passionate about Open Source Dream big, code bigger ☕

OpenRouter is pay as you go so it's not a fixed subscription. OpenCode has "Zen" which is pay as you go, and "Go" which is a fixed monthly subscription.

It's open source go ahead and make a pr

My timeline is full of talk about Claude, Codex, Claude vs Codex, Mythos this, Fable that.... Guys, grow some balls and use open weight models in OpenCode. You don't need the top tier expensive LLMs for 90% of use cases.

Execution memory in opencode :) @OpenAI @opencode

6. OpenCode · 150,000 stars in 2026 The most-starred open-source AI coding agent of 2026. OpenCode crossed 150,000 GitHub stars. 850 contributors. 11,000 commits. 6.5 million developers using it monthly. It does what Claude Code does read your codebase, edit files, run commands, manage git, chain multi-step tasks. But it lets you plug in any model from 75 providers. GPT-5. Claude Opus. Gemini 3 Pro. DeepSeek V4. Llama 4. Mistral. Qwen3. Local models via Ollama at zero API cost. In January 2026, Anthropic blocked OpenCode from accessing Claude through OAuth. OpenCode doubled its stars in two months. The community voted with their installs. github.com/anomalyco/opencod…

5. Everything Claude Code · 100,000 stars in 4 days A developer won an Anthropic hackathon in September 2025. Then he open-sourced what he built. And it crossed 100,000 GitHub stars in under a week. It is called Everything Claude Code. The de facto starting point for any team using AI coding tools at scale. 28 specialized agents. 119 skills. Hooks for Claude Code, Cursor, Codex, OpenCode. Memory persistence. Security scanning. Production-grade rules. It fixes the problem every developer hits in week two of AI coding the agent is smart but keeps forgetting your conventions, keeps ignoring your patterns, keeps making the same category of mistake in slightly different ways every session. Everything Claude Code fixes that. Permanently. 100,000 stars. 28 agents. 119 skills. MIT license. Free. github.com/anthropics/everyt…

4. Open Design · 20,000 stars in 6 days Anthropic released Claude Design on April 17, 2026. Eleven days later, the open-source community released the free clone. It hit 20,000 GitHub stars in 6 days. It is called Open Design. Local-first. Web-deployable. BYOK at every layer. Works with 16 different AI agents Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and 11 others. 72 brand-grade design systems built in. Linear. Stripe. Vercel. Apple. Tesla. Spotify. Every major brand. Each one a single file that tells the AI how to design in that brand's exact visual language. 31 composable design skills. Built-in Critique Theater a five-panelist AI Design Jury that scores every artifact before it ships. The category Anthropic launched lasted 11 days as proprietary before the open-source equivalent existed. github.com/nexu-io/open-desi…