Bringing your (k)nowledge to Antigravity

Arun, the developer of the Nowledge Mem Google Antigravity plugin, has released the plugin as open source under the nowledge-co/nowledge-mem-google-antigravity repository, integrating Nowledge Mem's persistent personal knowledge base with Google Antigravity 2.0's plugin architecture. The plugin provides AI agents with situational context bundles, standing rules, compiled agent skills, and a unified filesystem, supporting local embedding models via Lemonade Server. The plugin is designed for low latency, offline resilience, and developer control, and is now maintained by Nowledge Labs.

Republication note:Republished with the author’s permission from the original post on abn.is , published 24 July 2026. Arun built the Google Antigravity plugin and donated it to Nowledge Labs, where it now lives at nowledge-co/nowledge-mem-google-antigravity . The technical content, headings, code, and screenshots are his. Nowledge Labs made four changes, none to the substance: the original’s opening says “we explain how we designed and built”, which under Arun’s byline on our own blog would read as though we built it, so it is “I explain how the plugin was designed and built” here; the original’s closing paragraph, which invites readers to contact Arun and points them to our posts, is omitted because that second pointer is circular here; the original’s callout boxes appear as blockquotes, which this blog renders instead; and the five diagrams are rendered inline from the original’s own Mermaid sources, so their labels sit in the page text rather than locked inside an image. AI coding assistants are fast and capable, but out of the box every new conversation starts empty. Past bug fixes, architectural choices, domain-specific gotchas, and preferred workflows live only in your head or disappear into long chat logs. Nowledge Mem fixes this by providing your AI agents with a persistent personal knowledge base storing atomic memories, daily working memory briefings, standing rules, and executable skills with evidence tracing . AI tools change. Your memory should compound: Mem carries conversations, decisions, and what your agents discover across tools. Every session builds on what came before and leaves the next one smarter. With Google Antigravity 2.0, Google introduced a plugin architecture for agent customization. In this post, I explain how the nowledge-mem-google-antigravity plugin was designed and built: a hybrid integration focused on low latency, offline resilience, and developer control. The plugin source lives at nowledge-co/nowledge-mem-google-antigravity https://github.com/nowledge-co/nowledge-mem-google-antigravity . 1. What Nowledge Mem Brings to the Table Nowledge Mem is an active personal knowledge engine for AI agents rather than a passive log store. Key capabilities Nowledge Mem delivers: Situational Context Bundles : Compiles active initiatives, focus areas, and memory references into a startup briefing <nowledge context bundle . Standing Rules : Global and agent-specific behavioral constraints security redaction, Flatpak D-Bus rules, code conventions enforced automatically across sessions. Compiled Agent Skills : Repeatable procedures SKILL.md bundles compiled from real past work, verified against test cases, and assigned trust badges Checked vs. Proven . Nowledge FS : A unified, path-first virtual filesystem mem fs /memories , /threads , /wiki , /skills for exploring knowledge trees cleanly. Using local models for your knowledge embedding inferencing needsNowledge Mem supports local models out of the box. It supports both GPU and CPU bound embedding models as well as on device inferencing for background intelligence tasks. I, personally, use Lemonade Server for managing local models with it also using my NPU for embedding. Nowledge Mem supports Lemonade as a first class LLM Provider . 2. The Google Antigravity 2.0 Plugin Architecture Google Antigravity 2.0 defines plugins as namespaced packages that bundle all agent customization types into a single structure: nowledge-mem-google-antigravity/ ├── plugin.json Required manifest ├── mcp config.json MCP Server definitions ├── hooks.json PreInvocation, PreToolUse, and Stop lifecycle hooks ├── rules/ Always-on system rules │ └── nowledge-mem.md └── skills/ Bundled agent skills ├── nmem-memory-search/ ├── nmem-skill-load/ └── nmem-thread-save/ When Antigravity starts, it scans two plugin locations: Workspace Level : <workspace-root /.agents/plugins/ project-specific . Global Level : ~/.gemini/config/plugins/ available across all projects . 3. Key Design Decisions & Architectural Rationale Connecting a local or remote knowledge base to an autonomous agent engine requires balancing three engineering constraints: Latency : Hook execution must complete in milliseconds without blocking the developer. Resilience : Network blips or sandboxed environment limits must never crash a session or lose data. UX Control : Developers should approve significant state changes without repetitive confirmation prompts. Here is the technical rationale behind our core architectural decisions. A. The 3 Startup Channels Context Economics Rationale To eliminate cold starts without bloating model prompts, the plugin initializes Antigravity through three complementary channels: Design Rationale Context Slicing vs. Prompt Bloat Inlining an entire knowledge graph into system prompts causes severe context bloat and expensive KV cache penalties. By splitting startup knowledge into 3 distinct layers: Channel 1 PreInvocation Hook injects only today’s active briefing and direct memory links nowledgemem://memory/<id .Channel 2 Always-On System Rules sets persistent behavioral boundaries.Channel 3 Available Skills Index provides lightweight pointers, deferring full skill body retrieval until an active task explicitly requires it. B. Tiered Transport Access Performance & Sandboxing Rationale Spawning CLI subprocesses for background hooks adds 300 to 500ms of latency per invocation. To keep execution sub-30ms, we implemented a 3-tier hybrid transport hierarchy in hooks/nmem shared.py : Design Rationale Tiered Access & Sandbox Security Tier 1 Native Python HTTP REST : Uses Python’s zero-dependency urllib.request to query /context , /working-memory , or /threads/import directly over HTTP <30ms . For remote Mem endpoints, nmem shared.py automatically injects Authorization: Bearer and X-MEM-API-Key headers.Why native HTTP first?Subprocess instantiation subprocess.run incurs heavy OS overhead. Direct REST queries drop hook latency from ~400ms to <30ms, ensuring session initialization never stalls developer flow.Tier 2 Multi-Path System CLI : If HTTP fails or local CLI tools are required, falls back to nmem .Why multi-path resolution?In sandboxed tool subshells BypassSandbox: false , symlinks in user directories ~/.local/bin/nmem are often hidden or blocked if they point outside the active workspace. nmem shared.py dereferences symlinks and checks canonical system package paths /usr/lib/nowledge-mem/nmem , /usr/lib64/nowledge-mem/nmem , guaranteeing shell execution reliability inside strict sandboxes.Tier 3 Local Buffer Queue : If the backend is completely unreachable when a session ends such as offline laptop work , session-end.py writes the session transcript payload to a file-locked offline queue ~/.nowledge-mem/antigravity unsynced.json .Why offline queueing?Session data and learning proposals should never be dropped due to network blips. A background retry worker flushes queued sessions automatically upon reconnection. C. Dynamic MCP Configuration Sync Git Hygiene Rationale When Nowledge Mem runs on a remote server or Tailscale network like https://mem.example.com , the client’s ~/.nowledge-mem/config.json stores the remote apiUrl and apiKey . However, Antigravity’s MCP client reads mcp config.json . If mcp config.json hardcodes http://127.0.0.1:14242 , MCP tools would fail with 403 Forbidden . To solve this cleanly: - On session start, session-start.py invokes nmem shared.sync mcp config file . - It resolves the effective URL/Key NMEM env vars → ~/.nowledge-mem/config.json → 127.0.0.1:14242 . - If pointing to a remote server, it updates mcp config.json on disk automatically with the remote /mcp/ endpoint and injects Authorization: Bearer and X-MEM-API-Key headers. { "mcpServers": { "nowledge-mem": { "serverUrl": "https://mem.example.com/mcp/", "headers": { "APP": "Google Antigravity", "Authorization": "Bearer nmem sec ...", "X-MEM-API-Key": "nmem sec ..." } } } } Design Rationale Git Hygiene The mcp config.json file is listed in .gitignore . Developers and contributors frequently git clone or symlink the plugin repository. Dynamically updating mcp config.json at session start to point to personal remote endpoints would cause annoying git status diffs. By ignoring mcp config.json in Git, local runtime configuration sync happens in place without dirtying working trees. D. Zero-Latency Host Skill Connection & Syncing Nowledge Mem compiles and crystallizes skills on your server. To ensure active skills are automatically connected and kept up-to-date in Antigravity: During session start, session-start.py launches a non-blocking background daemon thread: def sync host skills async : Connect host agent 'antigravity' & refresh client assets run nmem command "skills", "connect", "antigravity" run nmem command "skills", "sync" Design Rationale Asynchronous Execution & Race Condition Handling Why Background Async?Running nmem skills connect and nmem skills sync synchronously at startup would force developers to wait 1 to 2 seconds for network roundtrips. Executing in a background daemon thread adds 0ms overhead to session startup.Race Condition Fallback: If an agent triggers a skill command immediately on turn 1 before the background sync thread completes, the plugin uses the local .agents/skills/ cache or falls back to direct REST API fetching, preventing execution stalls. E. Optimistic Thread Tail Reconciliation Data Integrity Rationale When a long-running Antigravity session stops, saving the transcript via standard append operations could create duplicate messages if the session log was partially written earlier. To solve this, hooks/session-end.py utilizes Nowledge Mem’s POST /threads/{id}/reconcile-tail endpoint: Design Rationale Optimistic Tail Reconciliation Naive transcript appending breaks down when long conversations are resumed or partially flushed. reconcile-tail uses optimistic tail matching: it compares existing remote messages with new log steps, calculates matched count the number of unchanged leading messages , and safely replaces only the modified tail. If an offline session payload is flushed later from antigravity unsynced.json , the retry worker evaluates the same tail-matching logic upon reconnection. F. Standardized Domain Namespacing nmem-<domain -<action All 10 plugin skills follow a uniform naming pattern nmem-<domain -<action : skills/ ├── nmem-fs-explore/ Navigation & tree exploration ├── nmem-memory-distill/ Atomic memory distillation ├── nmem-memory-search/ Deep & semantic memory recall ├── nmem-memory-working/ Daily working memory reader ├── nmem-skill-load/ On-demand skill discovery & injection ├── nmem-skill-manage/ Workspace skill manager & suggestion engine ├── nmem-skill-propose/ Authoring & submitting new skills ├── nmem-status/ Diagnostic connection status ├── nmem-thread-handoff/ Resumable handoff summaries └── nmem-thread-save/ Full transcript importer This layout ensures skills group cleanly in IDE auto-completion, file listings, and prompt indexes, while providing matching slash command triggers e.g. /nmem-skill-load <query , /nmem-thread-save . 4. Developer in Control: Leveraging Antigravity’s Rich UX Instead of forcing developers into repetitive text-chat confirmation loops, the plugin leverages Antigravity’s native rich UI elements: 1. Interactive Multi-Select Prompts ask question When discovering or installing skills /nmem-skill-manage , the agent presents selectable checkboxes using ask question with is multi select: true , featuring recommended options first. An example interactive multi-select question 2. Proceed Plan Artifacts skills installation plan.md For larger workspace updates or memory distillations, the plugin writes a structured Markdown artifact to <appDataDir /brain/<conversation-id / with RequestFeedback: true : Skill Installation Plan | Skill ID | Trust Badge | Description | Target Path | Git Strategy | | :--- | :--- | :--- | :--- | :--- | | makefile-pattern | Proven | Makefile standards | .agents/skills/makefile-pattern/ | Git Exclude | | docker-build | Checked | Multi-stage Docker | .agents/skills/docker-build/ | Committed | Design Rationale Local Git Exclude vs. Committed Skills When users install skills into a workspace .agents/skills/<name /SKILL.md , some skills represent team-wide procedures which should be committed to Git , while others represent personal developer preferences. To prevent polluting team repositories with personal workflow rules, installer scripts support --ignore , which appends entries to .git/info/exclude rather than dirtying .gitignore . Draft plan with proceed button 5. In Practice: Dynamic Skill Loading /nmem-skill-load Here is how on-demand skill discovery works in practice during a real task: Ephemeral Mode Zero-Restart : Ingests the fetched SKILL.md body directly into the active turn context as a structured context block <skill instruction . This allows Antigravity to follow specialized instructions immediately for the current task without writing files to disk or requiring workspace restarts. Persistent Mode : Writes the skill to .agents/skills/<name /SKILL.md and appends .agents/skills/<name / to .git/info/exclude if the user prefers local-only isolation. Dynamic injection of a custom Makefile skill into a new session Conclusion & Getting Started By combining Google Antigravity 2.0’s plugin hooks with Nowledge Mem’s hybrid transport and rich UI interfaces, we created a knowledge integration that is fast, resilient, and developer-centric. Quick Setup Install the Plugin: mkdir -p ~/.gemini/config/plugins/nowledge-mem curl -sSL https://github.com/nowledge-co/nowledge-mem-google-antigravity/releases/latest/download/nowledge-mem-google-antigravity.tar.gz \ | tar -xz -C ~/.gemini/config/plugins/nowledge-mem Verify Connection: Restart Antigravity and run /nmem-status or check nmem status . Explore Knowledge: Use /nmem-memory-search , /nmem-skill-manage , or /nmem-skill-load <query to bring your personal knowledge base into your coding workflow. Global plugin skills available in any Antigravity conversation Once installed, you can use /nmem-status to check if everything configured and working properly There you have it; your personal context, engineering knowledge and rules all seamlessly integrated into your agentic development workflow and constantly growing the more you use it.