MCP servers and skills: search, filter by where they run, and compare.
Semantic search over past OpenCode conversations — local embeddings (Transformers.js), SQLite index, native plugin tools. Inspired by obra/episodic-memory, rebuilt natively for OpenCode.
SkillMIT★ 4Few starsNo key
Read-only Agent Skill for loading project-scoped OpenCode session context
SkillMITFew starsNo key
Intelligent web search routing for OpenCode with automatic tool selection, graceful fallbacks, and memory caching.
SkillMIT★ 2Few starsNo key
`Owl` Plugin - OpenCode Memory System plugin
SkillLink only★ 2Few stars
Project-local ticket, research, and memory workflows for OpenCode v2. Lean context, shared/private data separation, and reusable agent skills.
SkillLink onlyFew stars
SkillApache-2.0★ 5No key
A curated OpenCode configuration pack with specialized agents, skills, rules, and knowledge-graph tooling.
SkillMIT★ 9No key
A self-improving, memory-bounded multi-agent AI architecture for OpenCode. Turn static prompts into an autonomous, context-efficient learning loop.
SkillLink only★ 5
User Context Profile Skill for OpenCode - ???????Skill,???????????????,?AI??????????
SkillMITFew starsNo key
Convert OpenCode shared sessions into reusable, publishable AI agent skills with TRACE validation, security checks, and ZIP packaging.
SkillLink onlyFew stars
Production-ready multi-agent OpenCode configuration featuring automatic model fallback, persistent structured project memory, and reusable workflows. Built for modern AI tooling and forkability.
SkillMIT★ 2Few starsNo key
GenPark AI Agent Skill: opencode-automator (Inspired by GenPark 2026 Features)
SkillLink only★ 9
OPEN. CONFIGURABLE. Lightweight persistent markdown memory for OPENCODE sessions - inspired by Claude Code's auto-memory. Fully local and plug-in native. Primarily for personal use, but feel free to j
SkillMIT★ 1Few starsNo key
The pre-task artifact producer. Collects multi-source context (Jira+GitHub+atoms) into a user-reviewed immutable bundle before any AI task runs. Zero autonomy, 5 hard permission boundaries, replayable
SkillMIT★ 1Few starsNo key
GAIA — Generative AI Interface for Agents: one plans and decides the WHAT, specialist subagents execute the HOW — with project memory, context, techniques and verification built in — and an execution
SkillMIT★ 4Few starsNo key
Scan Claude Code, Codex, and Opencode sessions and visualize what eats your tokens — skills, thinking, tools, context.
SkillMIT★ 1Few starsNo key
An agent skill to evolve the quality of LLM-Wiki (Graphify) at test time.
SkillMIT★ 91No key
Orchestration-first Auto protocol for ZCode — phased work records, critical-thinking + simplicity lenses, verification protocol, independent-context personas via Explore. Port of opencode-auto.
SkillMIT★ 1Few starsNo key
OpenCode Agent Home scaffold and memory-seeding skills
SkillApache-2.0★ 3Few starsNo key
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, determi
SkillMIT★ 28kNo key
Turn any coding agent into an orchestrator: delegate code to a CLI agent via prompt files, verify with your own measurements, keep state on disk so nothing is lost to context compaction. Stack-agnosti
SkillLink only★ 2Few stars
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
SkillMIT★ 36kNo key
Branching conditional workflow execution tree builder
SkillLink only★ 9
Managed multi-agent system for OpenCode with one coordinator, risk-based routing, specialized roles, model pools and failover, durable memory, controlled context compaction and recovery, independent r
SkillMIT★ 7No key
Who stands behind it
