记忆与上下文
跨会话记忆、知识库、上下文压缩与检索增强。
- 148
- 232,673
- 76% 活跃停更 35
共收录 148 款插件
@openviking/opencode-pluginUnified OpenCode plugin for OpenViking repository retrieval and long-term memory
@cortexkit/magic-contextUnified CLI for Magic Context — setup, doctor, and migration across OpenCode, Pi, and OMP
@mem0/opencode-pluginMem0 persistent memory plugin for OpenCode — add, search, and manage memories across sessions
@zilliz/memsearch-opencodememsearch plugin for OpenCode — semantic memory search across sessions
opencode-acpActive Context Pruning — model-driven context management for OpenCode (hardened fork of DCP with 35 bug fixes)
openviking-opencodeOpenCode plugin for OpenViking — injects indexed repo context into the AI assistant and auto-installs the openviking skill
@mem9/opencodeOpenCode memory plugin — cloud-persistent AI agent memory with hybrid vector + keyword search via mem9
openviking-opencode-pluginUnified OpenCode plugin for OpenViking repository retrieval and long-term memory
opencode-hooksOpenCode hooks plugin - all hooks from oh-my-opencode without agents/tools/MCPs
claude-smartSelf-improving Claude Code, Codex, and OpenCode plugin that turns corrections into Preferences, Project-specific skills, and Shared skills
echoes-vault-opencodeEchoesVault — persistent memory plugin for OpenCode. Obsidian-style knowledge base with daily logs, encyclopedia pages, and session resumption.
opencode-claude-memoryOpenCode plugin for Claude Code memory: persistent, local-first shared memory with Claude Code-compatible Markdown files, auto extraction, and auto-dream
opencode-nowledge-memNowledge Mem plugin for OpenCode. Cross-tool knowledge with idle-event thread capture, Context Bundle, search, save, and handoffs.
@prismer/opencode-pluginEvolution-aware plugin for OpenCode — connects task execution to the Prismer Evolution Network for cross-agent learning
@hiai-gg/hiai-opencodeHiAi OpenCode Plugin — multi-agent orchestration for OpenCode with 10 agents, LSP tools, browser automation, Memory, Session management, and Caveman protocol
@rag-rat/plugin-opencodeopencode plugin for rag-rat: self-registers the rag-rat MCP server (semantic search, symbol/graph navigation, impact-surface preflight, repo memory) and wires session/grep/edit hooks through the shared agent-hook.
@fpytloun/opencode-mnemoryOpenCode plugin for mnemory — persistent AI memory with auto-recall, auto-capture, and explicit memory tools
@knikolov/opencode-plugin-simple-memoryPersistent project memory tools for OpenCode
opencode-session-recallEverything your agent ever did is already in the database — this plugin lets it look
opencode-ravenContext-saving search and on-demand MCP routing for OpenCode through focused Raven agents.
opencode-auto-fallbackAdvanced fallback plugin for OpenCode agents — model switching, retry with backoff, and context overflow handling
@sweetsophia/opencode-noosphere-memoryOpencode plugin for Noosphere memory: prompt-time auto-recall, optional idle auto-save, and explicit memory tools.
opencode-fractal-memoryFractal memory system for OpenCode with semantic search and automatic compression.
vibeostheogCost-aware delegation enforcer for OpenCode. Tracks model usage, routes Task subagents to cheaper tiers, surfaces cumulative savings in chat. Includes research audit, reporting framework, project memory, progressive scratchpad decadence, and trinity CLI f
@bojackduy/opencode-telescopeOpenCode TUI plugin for fuzzy and semantic search across local conversation history, session transcripts, and AI coding chats
hivemind-context-governanceContext-Aware Governance Layer for OpenCode - prevents drift and manages session state across lifecycles
@oxhive/opencode-hivemindHiveMind persistent memory plugin for OpenCode. Auto-registers MCP server and provides memory skills.
@jeffober/thatchPersistent memory for AI coding agents — local embeddings, SQLite stores, zero config. Works with OpenCode (as a plugin), Claude Code (as an MCP server), and Cursor (as an MCP server).
opencode-okf-contextOpenCode plugin: progressive disclosure + auto-unload for OKF (Open Knowledge Format) knowledge bundles. Inspired by DCP's outbound-only context transformation.
@aerovato/operator-opencodeOperator Memory: durable context for agent-driven development.
@geohar/opencode-cribsheetOpenCode plugin: run the crib (cribsheet) memory + code-index MCP server via sharedserver, register its endpoint, inject the reach-for-crib directive, and ship the /crib command. Stands down when a combiner already serves crib.
@audaxic/memory-opencodeOpenCode plugin for Audaxic Memory - automatically saves conversation facts to your persistent memory layer
opencode-mnemosyneOpenCode plugin for local persistent memory using Mnemosyne — offline semantic search, no cloud required
code-memory-opencodeOpenCode plugin: auto-retrieve and auto-learn against a local code-memory backend.
opencode-large-image-optimizerOpenCode plugin that automatically resamples and compresses oversized images to prevent API errors and context window bloat
opencode-itsukiItsuki memory for OpenCode: bounded recall before every new human turn, exactly-once capture after each settled one.
@eleboucher/opencode-meminiAutomatic cross-session memory for opencode via memini — recall before each turn, capture after.
@gintasz/opencode-neuralyzerAI agent harness tool allowing it to wipe its own session context and re-run the first message
@manti-by/openwikiOpenCode plugin that scaffolds a per-project session wiki (commands, templates, and the wiki/ directory). Install-only — no background agent, no event hooks.
opencode-hypaOpenCode plugin that rewrites bash tool calls through Hypa for local, deterministic output compression.
opencode-model-scoutopencode plugin that auto-discovers models from OpenAI-compatible providers and enriches them with context window sizes, capability flags, and model metadata. Supports Atlas, Ollama, oMLX, vLLM, TGI, SGLang, LM Studio, KoboldCpp, llama.cpp, and LocalAI.
@get-keel/opencode-pluginKeel enforcement plugin for OpenCode — blocks rule violations at tool.execute.before, outside the agent's context window.
@mathew-cf/opencode-memoryPersistent cross-session memory for OpenCode — a hybrid keyword + semantic search layer over a local markdown knowledge base, plus session history tools and guardrails that nudge agents to use them.
opencode-mempalaceOpenCode plugin for MemPalace memory system — auto-registers MCP server, injects memory protocol into system prompt, and loads context on session start
@cioffi_ai/opencode-memoryLocal-first persistent memory for OpenCode using a WRITE → DREAM → SURFACE lifecycle.
@josxa/opencode-recallOpenCode plugin that adds semantic + lexical recall over your local session history, with cursor-paginated ChatML transcript reads.
opencode-ledgerOpenCode plugin that tracks confirmed findings and injects them to prevent re-investigation
@foae/opencode-timingsOpenCode TUI sidebar panel showing per-session timing: total API/inference time, wall-clock, turns, average and slowest turn. Zero context-window pollution.
@ghilteras/opencode-reasoning-prunerPrunes historical reasoning parts from the message history sent to the LLM (keeping the last turn's), saving context window and tokens on reasoning models. Model-agnostic; uses the idiomatic experimental.chat.messages.transform hook.
opencode-mempalace-persistenceOpenCode plugin — auto-sync conversations to MemPalace memory in real-time. No forced wings, KG extraction via MCP tools.
@enerjizeit/opencode-session-managerNever lose an opencode AI conversation — pin, back up, restore & auto-cleanup sessions, via natural language.
@devwellington/opencode-context-pluginOpenCode plugin that saves session context to .opencode/context-session/ after compaction and session end
@memorylake/opencode-pluginMemory Lake for opencode: cross-device, cross-client long-term memory, including memories written from Claude Code that opencode cannot otherwise see.
opencode-plugin-mempalaceAn OpenCode plugin that integrates MemPalace's lifetime memory (L0-L3 memory stack, AAAK compression, auto context saving) into the OpenCode terminal assistant.
opencode-plugin-cost-guardThe opencode cost guard plugin: stop AI token waste. Live session watch, runaway context detection, auto-compaction, spend budgets & alerts, JSONL savings reports. Cuts LLM API spend by capping paid-model context and taming cache replay.