agentpluginsdirectory
V0v1kkk avatar

openviking-memory

v0.1.0

by V0v1kkk · author: Vladimir Rogozhin

Native OpenViking long-term memory integration for Antigravity (MCP tools + automatic recall + non-blocking background capture).

What openviking-memory does, in the publisher's words

A native, zero-dependency plugin that connects Google Antigravity 2.0 to an OpenViking long-term memory server.

Unlike standard MCP servers that require the model to manually call search tools for every turn, this plugin hooks directly into Antigravity's execution lifecycle:

  • Auto-Recall (PreInvocation): Injects relevant memories into the prompt before the model runs.
  • Auto-Capture (Stop): Asynchronously captures completed conversation turns in a detached background worker without UI latency.
  • Auto-Distillation: Automatically distills sessions into curated memories when token limits are reached or sessions become idle.
  • Transparent Auto-Recall
  • Automatically executes semantic search on OpenViking before the first model call of each user turn.
  • Per-turn SHA-256 hash deduplication ensures recall runs exactly once per user prompt (never repeated during internal tool-call loops).

From the project README, punctuation lightly normalized · Open the README on GitHub

Skills
1
MCP servers
0
Stars
0
License
MIT
Repo created
2026-08-17
Last pushed
2026-08-17
Publisher type
User
Version
0.1.0

Links

Skills · 1

openviking-memory
Use OpenViking long-term memory in Antigravity. Background hooks handle automatic recall and capture. Use MCP tools (search, read, remember) when manual exploration of memories, resources, or explicit fact preservation is needed.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

Category

Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Keywords

openviking · antigravity · memory · mcp · lifecycle-hooks · agent-plugins

Related by publisher and keywords

  • freecad-engineeringV0v1kkk

    Editable, evidence-backed FreeCAD modeling and small-part engineering workflows for AI agents.

  • openvikingvolcengine

    Semantic long-term memory and context engine for coding agents. Recall prior knowledge with the find/search/read MCP tools and persist durable facts with remember/write, backed by an OpenViking server.

  • mempalace-coderergards

    Local-first semantic memory for coding agents, packaged with a minimal-profile MCP server and LLM skill.

  • redisHiAi-gg

    Inspect and work with Redis: keys, values, TTLs, hashes, lists, sets, streams, memory, and diagnostics via Redis' official MCP server.

  • centricmem-skillzeyu-j

    Hosted CentricMem librarian: organise and retrieve Markdown memory via host MCP.

  • hindsightvectorize-io

    Long-term memory for AI agents. Recalls relevant past context before you answer and retains durable facts as you work, backed by Hindsight's retain/recall/reflect memory engine.

Add the verified badge to your README[![Verified by AgentPluginsDirectory.com against Schema 1.0.0](https://agentpluginsdirectory.com/badge.svg)](https://agentpluginsdirectory.com/plugins/openviking-memory)

✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.