diff --git a/README.md b/README.md index 860e9b98a..1ce701e7a 100644 --- a/README.md +++ b/README.md @@ -33,9 +33,11 @@ -> Anthropic wants you locked in. Claude Code's a nice prison, but it's still a prison. +> Anthropic [**blocked OpenCode because of us.**](https://x.com/thdxr/status/2010149530486911014) **Yes this is true.** +> They want you locked in. Claude Code's a nice prison, but it's still a prison. > -> We don't do lock-in here. We ride every model. Claude for orchestration. GPT for reasoning. Kimi for speed. Gemini for vision. The future isn't picking one winnerβ€”it's orchestrating them all. Models get cheaper every month. Smarter every month. No single provider will dominate. We're building for that open market, not their walled gardens. +> We don't do lock-in here. We ride every model. Claude / Kimi / GLM for orchestration. GPT for reasoning. Minimax for speed. Gemini for creativity. +> The future isn't picking one winnerβ€”it's orchestrating them all. Models get cheaper every month. Smarter every month. No single provider will dominate. We're building for that open market, not their walled gardens.
@@ -136,23 +138,23 @@ Even only with following subscriptions, ultrawork will work well (this project i - [GLM Coding Plan ($10)](https://z.ai/subscribe) - If you are eligible for pay-per-token, using kimi and gemini models won't cost you that much. -| | Feature | What it does | -| :---: | :--------------------------- | :---------------------------------------------------------------------------------------------------------------------------------- | -| πŸ€– | **Discipline Agents** | Sisyphus orchestrates Hephaestus, Oracle, Librarian, Explore. A full AI dev team in parallel. | -| ⚑ | **`ultrawork` / `ulw`** | One word. Every agent activates. Doesn't stop until done. | -| πŸšͺ | **[IntentGate](https://factory.ai/news/terminal-bench)** | Analyzes true user intent before classifying or acting. No more literal misinterpretations. | -| πŸ”— | **Hash-Anchored Edit Tool** | `LINE#ID` content hash validates every change. Zero stale-line errors. Inspired by [oh-my-pi](https://github.com/can1357/oh-my-pi). [The Harness Problem β†’](https://blog.can.ac/2026/02/12/the-harness-problem/) | -| πŸ› οΈ | **LSP + AST-Grep** | Workspace rename, pre-build diagnostics, AST-aware rewrites. IDE precision for agents. | -| 🧠 | **Background Agents** | Fire 5+ specialists in parallel. Context stays lean. Results when ready. | -| πŸ“š | **Built-in MCPs** | Exa (web search), Context7 (official docs), Grep.app (GitHub search). Always on. | -| πŸ” | **Ralph Loop / `/ulw-loop`** | Self-referential loop. Doesn't stop until 100% done. | -| βœ… | **Todo Enforcer** | Agent goes idle? System yanks it back. Your task gets done, period. | -| πŸ’¬ | **Comment Checker** | No AI slop in comments. Code reads like a senior wrote it. | -| πŸ–₯️ | **Tmux Integration** | Full interactive terminal. REPLs, debuggers, TUIs. All live. | -| πŸ”Œ | **Claude Code Compatible** | Your hooks, commands, skills, MCPs, and plugins? All work here. | -| 🎯 | **Skill-Embedded MCPs** | Skills carry their own MCP servers. No context bloat. | -| πŸ“‹ | **Prometheus Planner** | Interview-mode strategic planning before any execution. | -| πŸ” | **`/init-deep`** | Auto-generates hierarchical `AGENTS.md` files throughout your project. Great for both token efficiency and your agent's performance | +| | Feature | What it does | +| :---: | :------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| πŸ€– | **Discipline Agents** | Sisyphus orchestrates Hephaestus, Oracle, Librarian, Explore. A full AI dev team in parallel. | +| ⚑ | **`ultrawork` / `ulw`** | One word. Every agent activates. Doesn't stop until done. | +| πŸšͺ | **[IntentGate](https://factory.ai/news/terminal-bench)** | Analyzes true user intent before classifying or acting. No more literal misinterpretations. | +| πŸ”— | **Hash-Anchored Edit Tool** | `LINE#ID` content hash validates every change. Zero stale-line errors. Inspired by [oh-my-pi](https://github.com/can1357/oh-my-pi). [The Harness Problem β†’](https://blog.can.ac/2026/02/12/the-harness-problem/) | +| πŸ› οΈ | **LSP + AST-Grep** | Workspace rename, pre-build diagnostics, AST-aware rewrites. IDE precision for agents. | +| 🧠 | **Background Agents** | Fire 5+ specialists in parallel. Context stays lean. Results when ready. | +| πŸ“š | **Built-in MCPs** | Exa (web search), Context7 (official docs), Grep.app (GitHub search). Always on. | +| πŸ” | **Ralph Loop / `/ulw-loop`** | Self-referential loop. Doesn't stop until 100% done. | +| βœ… | **Todo Enforcer** | Agent goes idle? System yanks it back. Your task gets done, period. | +| πŸ’¬ | **Comment Checker** | No AI slop in comments. Code reads like a senior wrote it. | +| πŸ–₯️ | **Tmux Integration** | Full interactive terminal. REPLs, debuggers, TUIs. All live. | +| πŸ”Œ | **Claude Code Compatible** | Your hooks, commands, skills, MCPs, and plugins? All work here. | +| 🎯 | **Skill-Embedded MCPs** | Skills carry their own MCP servers. No context bloat. | +| πŸ“‹ | **Prometheus Planner** | Interview-mode strategic planning before any execution. | +| πŸ” | **`/init-deep`** | Auto-generates hierarchical `AGENTS.md` files throughout your project. Great for both token efficiency and your agent's performance | ### Discipline Agents diff --git a/docs/guide/installation.md b/docs/guide/installation.md index ea33e0498..cdb5ed3b3 100644 --- a/docs/guide/installation.md +++ b/docs/guide/installation.md @@ -194,11 +194,11 @@ GitHub Copilot is supported as a **fallback provider** when native providers are When GitHub Copilot is the best available provider, oh-my-opencode uses these model assignments: -| Agent | Model | -| ------------- | -------------------------------- | -| **Sisyphus** | `github-copilot/claude-opus-4-6` | -| **Oracle** | `github-copilot/gpt-5.2` | -| **Explore** | `opencode/gpt-5-nano` | +| Agent | Model | +| ------------- | --------------------------------------------------------- | +| **Sisyphus** | `github-copilot/claude-opus-4-6` | +| **Oracle** | `github-copilot/gpt-5.2` | +| **Explore** | `opencode/gpt-5-nano` | | **Librarian** | `zai-coding-plan/glm-4.7` (if Z.ai available) or fallback | GitHub Copilot acts as a proxy provider, routing requests to underlying models based on your subscription. @@ -209,12 +209,12 @@ Z.ai Coding Plan provides access to GLM-4.7 models. When enabled, the **Libraria If Z.ai is the only provider available, all agents will use GLM models: -| Agent | Model | -| ------------- | -------------------------------- | -| **Sisyphus** | `zai-coding-plan/glm-4.7` | -| **Oracle** | `zai-coding-plan/glm-4.7` | -| **Explore** | `zai-coding-plan/glm-4.7-flash` | -| **Librarian** | `zai-coding-plan/glm-4.7` | +| Agent | Model | +| ------------- | ------------------------------- | +| **Sisyphus** | `zai-coding-plan/glm-4.7` | +| **Oracle** | `zai-coding-plan/glm-4.7` | +| **Explore** | `zai-coding-plan/glm-4.7-flash` | +| **Librarian** | `zai-coding-plan/glm-4.7` | #### OpenCode Zen @@ -222,12 +222,12 @@ OpenCode Zen provides access to `opencode/` prefixed models including `opencode/ When OpenCode Zen is the best available provider (no native or Copilot), these models are used: -| Agent | Model | -| ------------- | -------------------------------- | -| **Sisyphus** | `opencode/claude-opus-4-6` | -| **Oracle** | `opencode/gpt-5.2` | -| **Explore** | `opencode/gpt-5-nano` | -| **Librarian** | `opencode/glm-4.7-free` | +| Agent | Model | +| ------------- | -------------------------- | +| **Sisyphus** | `opencode/claude-opus-4-6` | +| **Oracle** | `opencode/gpt-5.2` | +| **Explore** | `opencode/gpt-5-nano` | +| **Librarian** | `opencode/glm-4.7-free` | ##### Setup @@ -263,41 +263,41 @@ Not all models behave the same way. Understanding which models are "similar" hel **Claude-like Models** (instruction-following, structured output): -| Model | Provider(s) | Notes | -|-------|-------------|-------| -| **Claude Opus 4.6** | anthropic, github-copilot, opencode | Best overall. Default for Sisyphus. | -| **Claude Sonnet 4.6** | anthropic, github-copilot, opencode | Faster, cheaper. Good balance. | -| **Claude Haiku 4.5** | anthropic, opencode | Fast and cheap. Good for quick tasks. | -| **Kimi K2.5** | kimi-for-coding | Behaves very similarly to Claude. Great all-rounder. Default for Atlas. | -| **Kimi K2.5 Free** | opencode | Free-tier Kimi. Rate-limited but functional. | -| **GLM 5** | zai-coding-plan, opencode | Claude-like behavior. Good for broad tasks. | -| **Big Pickle (GLM 4.6)** | opencode | Free-tier GLM. Decent fallback. | +| Model | Provider(s) | Notes | +| ------------------------ | ----------------------------------- | ----------------------------------------------------------------------- | +| **Claude Opus 4.6** | anthropic, github-copilot, opencode | Best overall. Default for Sisyphus. | +| **Claude Sonnet 4.6** | anthropic, github-copilot, opencode | Faster, cheaper. Good balance. | +| **Claude Haiku 4.5** | anthropic, opencode | Fast and cheap. Good for quick tasks. | +| **Kimi K2.5** | kimi-for-coding | Behaves very similarly to Claude. Great all-rounder. Default for Atlas. | +| **Kimi K2.5 Free** | opencode | Free-tier Kimi. Rate-limited but functional. | +| **GLM 5** | zai-coding-plan, opencode | Claude-like behavior. Good for broad tasks. | +| **Big Pickle (GLM 4.6)** | opencode | Free-tier GLM. Decent fallback. | **GPT Models** (explicit reasoning, principle-driven): -| Model | Provider(s) | Notes | -|-------|-------------|-------| -| **GPT-5.3-codex** | openai, github-copilot, opencode | Deep coding powerhouse. Required for Hephaestus. | -| **GPT-5.2** | openai, github-copilot, opencode | High intelligence. Default for Oracle. | -| **GPT-5-Nano** | opencode | Ultra-cheap, fast. Good for simple utility tasks. | +| Model | Provider(s) | Notes | +| ----------------- | -------------------------------- | ------------------------------------------------- | +| **GPT-5.3-codex** | openai, github-copilot, opencode | Deep coding powerhouse. Required for Hephaestus. | +| **GPT-5.2** | openai, github-copilot, opencode | High intelligence. Default for Oracle. | +| **GPT-5-Nano** | opencode | Ultra-cheap, fast. Good for simple utility tasks. | **Different-Behavior Models**: -| Model | Provider(s) | Notes | -|-------|-------------|-------| -| **Gemini 3 Pro** | google, github-copilot, opencode | Excels at visual/frontend tasks. Different reasoning style. | -| **Gemini 3 Flash** | google, github-copilot, opencode | Fast, good for doc search and light tasks. | -| **MiniMax M2.5** | venice | Fast and smart. Good for utility tasks. | -| **MiniMax M2.5 Free** | opencode | Free-tier MiniMax. Fast for search/retrieval. | +| Model | Provider(s) | Notes | +| --------------------- | -------------------------------- | ----------------------------------------------------------- | +| **Gemini 3 Pro** | google, github-copilot, opencode | Excels at visual/frontend tasks. Different reasoning style. | +| **Gemini 3 Flash** | google, github-copilot, opencode | Fast, good for doc search and light tasks. | +| **MiniMax M2.5** | venice | Fast and smart. Good for utility tasks. | +| **MiniMax M2.5 Free** | opencode | Free-tier MiniMax. Fast for search/retrieval. | **Speed-Focused Models**: -| Model | Provider(s) | Speed | Notes | -|-------|-------------|-------|-------| -| **Grok Code Fast 1** | github-copilot, venice | Very fast | Optimized for code grep/search. Default for Explore. | -| **Claude Haiku 4.5** | anthropic, opencode | Fast | Good balance of speed and intelligence. | -| **MiniMax M2.5 (Free)** | opencode, venice | Fast | Smart for its speed class. | -| **GPT-5.3-codex-spark** | openai | Extremely fast | Blazing fast but compacts so aggressively that oh-my-opencode's context management doesn't work well with it. Not recommended for omo agents. | +| Model | Provider(s) | Speed | Notes | +| ----------------------- | ---------------------- | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------- | +| **Grok Code Fast 1** | github-copilot, venice | Very fast | Optimized for code grep/search. Default for Explore. | +| **Claude Haiku 4.5** | anthropic, opencode | Fast | Good balance of speed and intelligence. | +| **MiniMax M2.5 (Free)** | opencode, venice | Fast | Smart for its speed class. | +| **GPT-5.3-codex-spark** | openai | Extremely fast | Blazing fast but compacts so aggressively that oh-my-opencode's context management doesn't work well with it. Not recommended for omo agents. | #### What Each Agent Does and Which Model It Got @@ -305,10 +305,10 @@ Based on your subscriptions, here's how the agents were configured: **Claude-Optimized Agents** (prompts tuned for Claude-family models): -| Agent | Role | Default Chain | What It Does | -|-------|------|---------------|--------------| -| **Sisyphus** | Main ultraworker | Opus (max) β†’ Kimi K2.5 β†’ GLM 5 β†’ Big Pickle | Primary coding agent. Orchestrates everything. **Never use GPT β€” no GPT prompt exists.** | -| **Metis** | Plan review | Opus (max) β†’ Kimi K2.5 β†’ GPT-5.2 β†’ Gemini 3 Pro | Reviews Prometheus plans for gaps. | +| Agent | Role | Default Chain | What It Does | +| ------------ | ---------------- | ----------------------------------------------- | ---------------------------------------------------------------------------------------- | +| **Sisyphus** | Main ultraworker | Opus (max) β†’ Kimi K2.5 β†’ GLM 5 β†’ Big Pickle | Primary coding agent. Orchestrates everything. **Never use GPT β€” no GPT prompt exists.** | +| **Metis** | Plan review | Opus (max) β†’ Kimi K2.5 β†’ GPT-5.2 β†’ Gemini 3 Pro | Reviews Prometheus plans for gaps. | **Dual-Prompt Agents** (auto-switch between Claude and GPT prompts): @@ -316,28 +316,28 @@ These agents detect your model family at runtime and switch to the appropriate p Priority: **Claude > GPT > Claude-like models** -| Agent | Role | Default Chain | GPT Prompt? | -|-------|------|---------------|-------------| +| Agent | Role | Default Chain | GPT Prompt? | +| -------------- | ----------------- | ---------------------------------------------------------- | ---------------------------------------------------------------- | | **Prometheus** | Strategic planner | Opus (max) β†’ **GPT-5.2 (high)** β†’ Kimi K2.5 β†’ Gemini 3 Pro | Yes β€” XML-tagged, principle-driven (~300 lines vs ~1,100 Claude) | -| **Atlas** | Todo orchestrator | **Kimi K2.5** β†’ Sonnet β†’ GPT-5.2 | Yes β€” GPT-optimized todo management | +| **Atlas** | Todo orchestrator | **Kimi K2.5** β†’ Sonnet β†’ GPT-5.2 | Yes β€” GPT-optimized todo management | **GPT-Native Agents** (built for GPT, don't override to Claude): -| Agent | Role | Default Chain | Notes | -|-------|------|---------------|-------| -| **Hephaestus** | Deep autonomous worker | GPT-5.3-codex (medium) only | "Codex on steroids." No fallback. Requires GPT access. | -| **Oracle** | Architecture/debugging | GPT-5.2 (high) β†’ Gemini 3 Pro β†’ Opus | High-IQ strategic backup. GPT preferred. | -| **Momus** | High-accuracy reviewer | GPT-5.2 (medium) β†’ Opus β†’ Gemini 3 Pro | Verification agent. GPT preferred. | +| Agent | Role | Default Chain | Notes | +| -------------- | ---------------------- | -------------------------------------- | ------------------------------------------------------ | +| **Hephaestus** | Deep autonomous worker | GPT-5.3-codex (medium) only | "Codex on steroids." No fallback. Requires GPT access. | +| **Oracle** | Architecture/debugging | GPT-5.2 (high) β†’ Gemini 3 Pro β†’ Opus | High-IQ strategic backup. GPT preferred. | +| **Momus** | High-accuracy reviewer | GPT-5.2 (medium) β†’ Opus β†’ Gemini 3 Pro | Verification agent. GPT preferred. | **Utility Agents** (speed over intelligence): These agents do search, grep, and retrieval. They intentionally use fast, cheap models. **Don't "upgrade" them to Opus β€” it wastes tokens on simple tasks.** -| Agent | Role | Default Chain | Design Rationale | -|-------|------|---------------|------------------| -| **Explore** | Fast codebase grep | MiniMax M2.5 Free β†’ Grok Code Fast β†’ MiniMax M2.5 β†’ Haiku β†’ GPT-5-Nano | Speed is everything. Grok is blazing fast for grep. | -| **Librarian** | Docs/code search | MiniMax M2.5 Free β†’ Gemini Flash β†’ Big Pickle | Entirely free-tier. Doc retrieval doesn't need deep reasoning. | -| **Multimodal Looker** | Vision/screenshots | Kimi K2.5 β†’ Kimi Free β†’ Gemini Flash β†’ GPT-5.2 β†’ GLM-4.6v | Kimi excels at multimodal understanding. | +| Agent | Role | Default Chain | Design Rationale | +| --------------------- | ------------------ | ---------------------------------------------------------------------- | -------------------------------------------------------------- | +| **Explore** | Fast codebase grep | MiniMax M2.5 Free β†’ Grok Code Fast β†’ MiniMax M2.5 β†’ Haiku β†’ GPT-5-Nano | Speed is everything. Grok is blazing fast for grep. | +| **Librarian** | Docs/code search | MiniMax M2.5 Free β†’ Gemini Flash β†’ Big Pickle | Entirely free-tier. Doc retrieval doesn't need deep reasoning. | +| **Multimodal Looker** | Vision/screenshots | Kimi K2.5 β†’ Kimi Free β†’ Gemini Flash β†’ GPT-5.2 β†’ GLM-4.6v | Kimi excels at multimodal understanding. | #### Why Different Models Need Different Prompts @@ -446,6 +446,6 @@ Tell the user of following: 3. **Need precision?** Press **Tab** to enter Prometheus (Planner) mode, create a work plan through an interview process, then run `/start-work` to execute it with full orchestration. -4. You wanna know more? Checkout: [Overview Guide](./overview.md) +4. You wanna have your own agent- catalog setup? I can read the [docs](docs/guide/agent-model-matching.md) and set up for you after interviewing! That's it. The agent will figure out the rest and handle everything automatically.