A lightweight, token-efficient orchestrator layer. Enables parallel background task execution in OpenCode. Launch AI agents to work simultaneously on exploration and research while continuing with other tasks. Allows specifying custom models for each_agent via configuration.

🔗 View Repository

Replaces the default home-page tips with inspirational quotes for a more motivating OpenCode experience.

🔗 View Repository

Two plugins that improve agent identity awareness. AgentSelfIdentityPlugin injects a one-liner into the system prompt so the model knows which agent it's operating as. AgentAttributionToolPlugin exposes a tool for querying per-message agent attribution via the SDK, useful for agents that review multi-agent sessions.

🔗 View Repository

Gives the agent persistent, self-editable memory blocks inspired by Letta agents.

🔗 View Repository

Dynamic skills loader that discovers skills from project, user, and plugin directories.

🔗 View Repository

Use Gemini and Anthropic models for free via Google Antigravity IDE authentication.

🔗 View Repository

Fork of opencode-antigravity-auth that allows using multiple Google accounts with automatic rotation when rate limited.

🔗 View Repository

Two-phase session titling - instant keyword titles on user message, refined AI titles after response. Auto-selects cheapest model (flash/haiku/fast), respects custom titles, zero configuration needed.

🔗 View Repository

Background process management plugin for opencode.

🔗 View Repository

Claude Code-style background agents with async delegation and context persistence.

🔗 View Repository

Integration for Steve Yegge's beads issue tracker with /bd-* commands.

🔗 View Repository

Structured, persistent planning for OpenCode with local session state, /brhp commands, bounded planner history, and a TUI sidebar.

🔗 View Repository

A Claude Code plugin that acts as a safety net, catching destructive git and filesystem commands before they execute.

🔗 View Repository

An OpenCode plugin that reads your Claude Code Switch (CCS) configuration and automatically syncs the providers into your OpenCode config.

🔗 View Repository

Automatically discovers and injects Makefile targets, npm/pnpm/yarn/bun scripts, and local skills at startup. Type / to see and run all project commands.

🔗 View Repository

An opencode plugin that provides detailed token usage analysis for your AI sessions.

🔗 View Repository

CrewBee is an independent Agent Team framework for OpenCode. It lets users define reusable task/project-specific Agent Teams, project them into OpenCode agents, and switch between single-agent execution and multi-agent collaboration based on task complexity. It also includes built-in Team templates such as a Coding Team with review flow and completion criteria.

🔗 View Repository

Plugin for running multiple devcontainer instances with auto-assigned ports and branch-based isolation.

🔗 View Repository

Automatically loads direnv environment variables at session start. Perfect for Nix flakes.

🔗 View Repository

Official Dodo Payments plugin for OpenCode (also Claude Code, Codex, Cursor). Bundles eight integration skills (checkout, subscriptions, webhooks, usage-based billing, credits, license keys, BillingSDK, best practices) plus two MCP servers — a live API server with browser OAuth and a documentation search server. Distributed via npm as @dodopayments/opencode-plugin.

🔗 View Repository

Plugin that optimises token usage by pruning obsolete tool outputs from conversation context.

🔗 View Repository

MCP server with four tools (harness_reasoning, harness_code, harness_anti_deception, harness_memory) that AI agents can call on demand. Each tool returns a structured prompt the calling agent ingests before generating.

🔗 View Repository

OpenCode plugin that prevents agents/tools from reading or editing sensitive .env* files, while still allowing safe inspection via EnvSitter (keys + deterministic fingerprints; never values).

🔗 View Repository

FlowDeck adds a structured, multi-agent development workflow to OpenCode. It coordinates 25 specialist agents through a four-phase cycle — discuss, plan, execute, review — with persistent state that survives session restarts.

Key features:

• 25 specialist agents (architect, planner, coder, reviewer, tester, debugger, risk-analyst, policy-enforcer, and more)

• 24 reusable workflow skills (TDD, security scan, deploy check, code review, and more)

• 17 workflow commands for all project operations

• 15 pre-built orchestration flows including Spec-Driven Development (SDD)

• Persistent state via .planning/STATE.md — resume exactly where you left off

• Wave-based parallel execution for independent tasks

• AI Safety layer: patch trust scoring, edit gates, phase gating, arch constraint enforcement, failure replay, and regression prediction

• Deep System Hooks: context monitoring, session idle summaries, shell environment injection

• Built-in MCPs: Context7 (docs), Exa (web search), Grep.app (code search)

• Ensemble Reasoning via /fd-council for synthesized consensus from multiple agents

• Persistent Memory with SQLite for tool executions and session summaries

  
  
  🔗 View Repository

Plugin providing Claude Code-style hooks, specialized agents, and tools like gitingest.

🔗 View Repository

Authenticate the Opencode CLI with your Google account so you can use your existing Gemini plan.

🔗 View Repository

Create and publish GitHub releases with semantic versioning, tag management, and auto-generated release notes.

🔗 View Repository

An opencode plugin that exposes a native tool for querying Google AI Mode (SGE).

🔗 View Repository

Transforms AI-assisted coding with spec-driven workflows. Features 5-phase workflow (Plan, Research, Specify, Execute, Accept), contract gates for user confirmation, 12 specialized subagents, persistent memory system, wave-based execution with atomic commits, and deviation rules for handling unexpected situations.

🔗 View Repository

Brings gpt-image-2 (ChatGPT Images 2) image generation to OpenCode. When you sign into OpenCode with your ChatGPT account, generations are billed against your existing Plus / Pro / Business plan — no per-image API cost. An OpenAI API key path is also planned. Supports reference images for style guidance and edits.

🔗 View Repository

Creates focused handoff prompts for continuing work in a new session.

🔗 View Repository

Auto-captures evidence from tool interactions and materializes memories through a multi-gate pipeline. 4-layer activation engine selects the right memories per context. Replaces CLAUDE.md with structured, searchable, reviewable project memory. Local-first (sql.js WASM), zero cloud dependency.

🔗 View Repository

Unified plugin shipping 10 visible agents (Bob, Coder, Strategist, Critic, Guard, Researcher, Designer, Manager, Brainstormer, Vision) plus hidden Sub and Agent Skills. Bundles MCP wiring (playwright, stitch, sequential-thinking, firecrawl, rag, mempalace, context7, websearch, grep_app), LSP, skill materialization, and a multi-layer continuation system (todo enforcer, ralph-loop, ULTRAWORK auto-start) in one install.

🔗 View Repository

Give OpenCode persistent memory that survives context wipes, session restarts, and fresh chats. Honcho remembers what you're working on, durable preferences, and prior context across projects. Supports cloud and self-hosted deployments with configurable session strategies.

🔗 View Repository

Plugin-first entry point into the Kibi stack for OpenCode users. It adds context-aware guidance, routes durable code comments toward Kibi artifacts, runs non-blocking background sync and targeted validation checks, and helps keep repo knowledge branch-local and queryable.

copy

<br><br>
<a href="https://github.com/Looted/kibi">🔗 <b>View Repository</b></a>

Adds Kilo Gateway provider support to OpenCode.

🔗 View Repository

Biological memory model for AI coding agents. Features confidence decay/boost, Fuse.js fuzzy dedup, guide system with usage tracking, cross-references, cumulative backup, virtual session tracking, and universal memory injection via tool descriptions (works on Claude Desktop, Cursor, VS Code, Gemini CLI, opencode, and any MCP client). No API keys, no cloud, fully local JSONL storage. 20 MCP tools, 110 tests, MIT licensed.

copy

<br><br>
<a href="https://github.com/xenitV1/lemma">🔗 <b>View Repository</b></a>

Cache-aware context management that keeps long sessions productive. Background historian compresses old conversation into structured compartments while you keep working. Includes cross-session project memory, unified search across history/memories/facts, overnight dreamer for memory maintenance, and prompt-cache-safe deferred operations.

🔗 View Repository

Modal-based skill install, remove, list, and update workflow that avoids ANSI prompts while wrapping the skills CLI inside OpenCode.

🔗 View Repository

Structured workflow with session continuity, subagent orchestration, git worktree isolation, and AST-aware tools.

🔗 View Repository

Automatically injects the current model name into the chat context so the LLM is self-aware.

🔗 View Repository

Integrates Morph's Fast Apply API for faster code editing with lazy edit markers and unified diff output.

🔗 View Repository

Gives all OpenCode agents a shared persistent memory store where every agent can read and write. Each entry is tagged with the creating agent (plan, build, ask, review) so no context is lost between roles. Powered by the mnemoria Rust engine with hybrid BM25 + semantic search, CRC32 checksum chains, and an append-only binary format. Includes 7 tools and /mn-* slash commands.

🔗 View Repository

Background agents, pre-built tools (LSP/AST/MCP), curated agents, and a Claude Code compatible layer.

🔗 View Repository

Slimmed-down fork of oh-my-opencode focused on core agent orchestration. Features specialized sub-agents (Explorer, Oracle, Librarian, Designer, etc.), background task management, LSP/AST tools, tmux integration for live agent visibility, and MCP servers. Optimized to consume significantly fewer tokens.

🔗 View Repository

Connect and automatically fetch models from your Omniroute instance

🔗 View Repository

In the style of Grok 4.20, multiple agents are dispatched to answer the same query. Each one has a different system prompt (logical, creative, research-focused) and have to reach a consensus for the final output. The user can specify which provider/model they want to use and override the system prompt of each agent via config.

🔗 View Repository

A fully local agentic coding plugin that intercepts plan mode and opens an annotation UI in your browser. Select text to strikethrough, replace, insert, or comment — then approve the plan or request changes

🔗 View Repository

This plugin enables opencode to use OpenAI's Codex backend via ChatGPT Plus/Pro OAuth authentication.

🔗 View Repository

OpenCode plugin that lets agents actively adjust model reasoning effort during a session, with configurable system guidance and a tool for switching between valid reasoning-effort variants.

🔗 View Repository

Smart tmux integration for OpenCode that auto-spawns panes to stream agent output, supports flexible layouts and multi-port setups, and cleans up when sessions finish.

🔗 View Repository

OpenCode sidebar plugin that displays configured OhMyOpenAgent agents with lifecycle-based categories, collapsible sections, descriptions, and model information.

🔗 View Repository

Interactive terminal canvases (calendars, documents, flight booking) in tmux splits. Port of claude-canvas for OpenCode.

🔗 View Repository

OpenCode browser automation for Chromium-based browsers using a readable Manifest V3 extension, Node.js native messaging host, and OpenCode-native tools. Supports Chrome, Edge, Brave, Chromium, screenshots, CDP commands, DOM actions, downloads, console/network inspection, and controlled tab sessions.

🔗 View Repository

Share persistent Markdown memory between OpenCode and Claude Code using Claude Code-compatible paths and file formats.

🔗 View Repository

Coordinate parallel OpenCode agents with peer messaging, a shared task board, git worktree isolation, and a live dashboard.

🔗 View Repository

Use Claude code hooks definition and hook them to opencode hooks.

🔗 View Repository

OpenCode plugin and host helper that forward permission, question, and idle notifications from devcontainers to the host machine for desktop alerts and sound.

🔗 View Repository

Plugin to ignore directory/file based on pattern.

🔗 View Repository

Drop-in LiteLLM provider for OpenCode with zero configuration. Auto-detects a running LiteLLM proxy on common ports (4000, 8000, 8080), pulls every model from /v1/models, and registers them in OpenCode automatically — no model lists to hand-maintain. Smart name formatting, modality categorization (chat/embedding/image/audio), provider extraction, optional API-key auth, and a 5-second timeout so a slow proxy never blocks startup.

copy

<br><br>
<a href="https://github.com/yuseferi/opencode-litellm">🔗 <b>View Repository</b></a>

Sanitizes pasted logs before sending them to AI by redacting long quoted strings, JWT tokens, bcrypt hashes, and base64 blobs to reduce token usage and remove irrelevant noise.

🔗 View Repository

A persistent memory system for AI coding agents that enables long-term context retention across sessions using local vector database technology. Features dual memory scopes, web interface, auto-capture system, and multi-provider AI support.

🔗 View Repository

Orchestrates parallel OpenCode agents in tmux-isolated git worktrees with live inspection (capture/attach/diff), a dashboard overview, agent status reporting, and in-chat notifications. Supports DAG-based plans with autopilot/copilot/supervisor modes and a merge train with test gating and automatic rollback.

🔗 View Repository

OpenCode plugin for discovering models from OpenAI-compatible providers and API gateways, with provider and model filtering so users can avoid maintaining large configs or loading every model at once.

🔗 View Repository

Native OS notifications for OpenCode - know when tasks complete.

🔗 View Repository

An OpenCode plugin that adds push notifications through ntfy.sh.

🔗 View Repository

High-performance, minimalist plugin designed to bridge the gap between complex implementation strategies and autonomous execution. Selective context loading, zero-hallucination schemas, visible filesystem kanban.

🔗 View Repository

Lets users define local OpenCode provider and model aliases hydrated from existing models.dev metadata.

🔗 View Repository

Track quota and token usage across providers via automatic toasts and slash commands.

🔗 View Repository

Strategic roadmap planning and multi-agent coordination plugin. Provides project-wide planning capabilities.

🔗 View Repository

Session management plugin for OpenCode with multi-agent collaboration support.

🔗 View Repository

Instant inline text expansion for OpenCode. Type #snippet anywhere in your message and watch it transform. Brings DRY principles to prompt engineering with composable, shell-enabled snippets.

🔗 View Repository

Verification-gated OpenCode swarm with architect planning, independent review, test engineering, security checks, and resumable evidence.

🔗 View Repository

Enables syncing global opencode configurations across machines with public/private visibility options.

🔗 View Repository

Real-time LLM performance monitoring plugin for OpenCode. Tracks TTFT, TPS, latency, token usage, and cost per model with toast notifications and a TUI sidebar display.

🔗 View Repository

Displays a toast after each AI response with input/output tokens, cache hits, reasoning tokens, response latency, per-message cost, cumulative session cost, model identifier, and request count. Automatically aggregates tokens from subagent sessions spawned via the Task tool. Zero config — drop the file in and it works.

🔗 View Repository

Speaks assistant responses aloud when a session goes idle, with summary or full-text modes and local TTS backends.

🔗 View Repository

Checks if your pinned plugins have newer versions available and shows a notification.

🔗 View Repository

Turning raw OpenCode terminal logs into cozy 2D pixel office chaos. Watch your agents work, idle, and celebrate success in a bustling virtual office.

🔗 View Repository

- AI has an early-exit problem: it says "done" at 30 seconds while edge cases are untested, bugs remain, and docs are missing. - Workaholic enforces mandatory working time for AI until the timer hits zero. - Blocks premature "done" responses until timer expire, and require AI to call checkout() to end the task.

copy

<br><br>
<a href="https://github.com/RoderickQiu/opencode-workaholic">🔗 <b>View Repository</b></a>

Bundled multi-agent orchestration harness with 16 components in one install.

🔗 View Repository

Zero-friction git worktrees for OpenCode. Auto-spawns terminals, syncs files, cleans up on exit.

🔗 View Repository

Substitute unicode characters for ASCII. Em-dash (—) and en-dash (–) for hyphens (-); right arrow (→) for (->) and so on.

🔗 View Repository

Brings the BMAD (Breakthrough Method of Agile AI-Driven Development) methodology to OpenCode. Provides specialized agents for product management, architecture, development, and QA roles. Automates epic planning, feature breakdown, sprint workflows, and code reviews through a structured multi-agent pipeline.

🔗 View Repository

Check all your AI subscription quotas in one command. Supports OpenAI (Plus/Pro/Codex, etc.), Zhipu AI, Google Antigravity, and more.

🔗 View Repository

Give your AI assistant a distinct personality with customizable moods that drift over time.

🔗 View Repository

Exports metrics, logs, and traces from opencode sessions via OTLP/gRPC to any OpenTelemetry-compatible backend (Datadog, Honeycomb, Grafana Cloud, etc.). Instruments session lifecycle, token usage, cost, tool durations, and git commits — mirroring the same signals as Claude Code's monitoring.

🔗 View Repository

An automatic code review plugin for OpenCode CLI. Reviews staged changes when session goes idle, with configurable cooldown, multi-dimension analysis (code quality, security, performance, testing, documentation), severity levels, and auto-fix chain support.

🔗 View Repository

Automatically summarizes conversation context into structured session memory and injects it back into the system prompt every few turns — preserving user instructions, project context, decisions, and active references across long chats and compactions.

🔗 View Repository

…view the full README on GitHub.