Antigravity

ChatGPT for your codebase — works in Claude Code, Cursor, Codex, Windsurf & 4 more.

English · 中文 · Español

# 1 — Install (Claude Code plugin marketplace)
/plugin marketplace add study8677/antigravity-workspace-template
/plugin install antigravity@antigravity

# 2 — Pick LLM provider, build the knowledge base
/antigravity:ag-setup
/antigravity:ag-refresh

# 3 — Ask anything, grounded in real code with file paths + line numbers
/antigravity:ag-ask "How does auth work?"

99% factual · 2.1× faster than Codex CLI · works in any AI IDE. Head-to-head benchmark ↓ Codex CLI users — drop the antigravity: prefix; the same four slash commands ship there too.

Why Antigravity?

Cross-IDE repository knowledge engine for grounded codebase Q&A. Same .antigravity/ knowledge layer reads in every IDE; one engine, every host.

An AI Agent's capability ceiling = the quality of context it can read.

ag-refresh deploys a multi-agent cluster that autonomously reads your code — each module gets its own Agent that generates a knowledge doc. ag-ask routes questions to the right Agent, grounded in real code with file paths and line numbers.

Instead of handing Claude Code / Codex a repo-wide grep and making it hunt on its own, give it a ChatGPT for your repository.

Traditional approach:              Antigravity approach:
  CLAUDE.md = 5000 lines of docs     Claude Code calls ask_project("how does auth work?")
  Agent reads it all, forgets most   Router → ModuleAgent reads actual source, returns exact answer
  Hallucination rate stays high      Grounded in real code, file paths, and git history

| Problem | Without Antigravity | With Antigravity | |:--------|:-------------------|:-----------------| | Agent forgets coding style | Repeats the same corrections | Reads .antigravity/conventions.md — gets it right the first time | | Onboarding a new codebase | Agent guesses at architecture | ag-refresh → ModuleAgents self-learn each module | | Switching between IDEs | Different rules everywhere | One .antigravity/ folder — every IDE reads it | | Asking "how does X work?" | Agent reads random files | ask_project MCP → Router routes to the responsible ModuleAgent |

Architecture is files + a live Q&A engine, not plugins. Portable across any IDE, any LLM, zero vendor lock-in.

Head-to-Head Eval: Antigravity vs Codex CLI vs Claude Code (2026-05-09)

Asymmetric benchmark on three real-world Python codebases — fastapi/fastapi, psf/requests, fastapi/sqlmodel — asking each tool the same 36 questions across three difficulty bands. All three tools used gpt-5.5 with high reasoning effort; Codex and Claude had full read access to the workspace. Codex was the grader (4-axis 0–3 rubric, scores verified against actual source).

| Question type | Antigravity | Codex CLI | Claude Code | |:---|:---:|:---:|:---:| | 15 factual lookups | 179/180 (99%) | 179/180 (99%) | 178/180 (99%) | | 12 synthesis (project / arch tour) | 116/144 (81%) | 144/144 (100%) | 136/144 (94%) | | 9 audit / security | 105/108 (97%) | 104/108 (96%) | 98/108 (91%) |

Combined factual + audit (24 cells): Antigravity 284/288, Codex 283/288, Claude 276/288. Antigravity edges out both — at lower latency than Codex on every single question.

Latency (mean wall-clock per question, same proxy):

| Question type | Antigravity | Codex | Claude | |:---|:---:|:---:|:---:| | Factual | 56s | 119s | 42s | | Audit | 160s | 177s | 100s |

Antigravity is 2.1× faster than Codex on factual and on par with Codex on audit, while matching or beating it on correctness. Claude is fastest on audit but loses 7 percentage points of correctness.

Two engine fixes landed during the benchmark, both committed in this branch:

1. _ask_with_agent_md now surfaces project-level docs (conventions.md, module_registry.md, map.md, structure.md) into its answer prompts. Removes the "module knowledge does not include project-wide conventions" refusal pattern.
2. The structured-facts answer agents now have search_code, read_file, list_directory, read_file_metadata, search_by_type bound at runtime, so the LLM can grep and read actual source instead of paraphrasing the KG.

Full report (data, methodology, per-cell tables, caveats): artifacts/benchmark-2026-05-09/REPORT.md.

Quick Start

Plugin install for Claude Code / Codex CLI (recommended — the engine CLI auto-installs on first session via SessionStart hook):

# Claude Code
/plugin marketplace add study8677/antigravity-workspace-template
/plugin install antigravity@antigravity
/antigravity:ag-setup            # interactive: pick LLM provider, paste API key, writes .env
/antigravity:ag-refresh          # first refresh auto-creates .antigravity/
/antigravity:ag-ask "How does this project work?"

# Codex CLI (manual engine install — Codex hooks are not yet supported)
pipx install "git+https://github.com/study8677/antigravity-workspace-template.git#subdirectory=engine"
codex plugin marketplace add study8677/antigravity-workspace-template
/ag-setup
/ag-refresh
/ag-ask "How does this project work?"

Codex auto-discovers slash commands from the plugin's commands/ directory, so the same four commands work without the antigravity: namespace prefix. The raw CLI calls (ag-refresh --workspace ., ag-ask "..." --workspace .) also still work. If your Codex build supports MCP, register ag-mcp --workspace <project> separately.

# 1. Install engine + CLI
pip install "git+https://github.com/study8677/antigravity-workspace-template.git#subdirectory=cli"
pip install "git+https://github.com/study8677/antigravity-workspace-template.git#subdirectory=engine"

# 2. Configure .env with any OpenAI-compatible API key
cd my-project
cat > .env <<EOF
OPENAI_BASE_URL=https://your-endpoint/v1
OPENAI_API_KEY=your-key
OPENAI_MODEL=your-model
AG_ASK_TIMEOUT_SECONDS=120
EOF

# 3. Build knowledge base (ModuleAgents self-learn each module)
ag-refresh --workspace .

# 4. Ask anything
ag-ask "How does auth work in this project?"

# 5. (Optional) Register as MCP server for Claude Code
claude mcp add antigravity ag-mcp -- --workspace $(pwd)

pip install git+https://github.com/study8677/antigravity-workspace-template.git#subdirectory=cli
ag init my-project && cd my-project
# IDE entry files bootstrap into AGENTS.md; dynamic knowledge is in .antigravity/

See INSTALL.md for full details and troubleshooting.

Slash Commands

Same four slash commands ship to both Claude Code and Codex CLI. Claude namespaces them as /antigravity:<name>; Codex auto-discovers commands/ and surfaces the bare /<name> form. No retraining — same flow on both hosts.

| Claude Code | Codex CLI | Purpose | |---|---|---| | /antigravity:ag-setup | /ag-setup | First-time setup — pick LLM provider, write .env | | /antigravity:ag-refresh [quick] | /ag-refresh [quick] | Build / incrementally refresh the project knowledge base | | /antigravity:ag-ask <question> | /ag-ask <question> | Routed Q&A on the current codebase | | /antigravity:ag-init <name> | /ag-init <name> | Scaffold a new multi-agent repo from this template |

A typical first session is ag-setup → ag-refresh → ag-ask.