Infimium

The Private Context Layer & Super Brain for Your Codebase. Give AI agents persistent memory, deep dependency graphs, and instant code context -- 100% local, zero token bloat.

Demo

Why

Large repositories make agents read too much code or miss the right symbol. Infimium retrieves compact, relevant context before the agent starts editing.

200,000 lines of code
Agent reads everything -> context blown + expensive
grep "price calculation" -> misses calcPropertyValue()

tool: semantic_code_search
query: "price calculation logic"

-> services/property/calc.ts:142 · calcPropertyValue()
-> callers: getListingPrice(), estimatePropertyTax()

Quick Start

Requires Node.js 22.5+. From your project folder:

cd /path/to/your/project
npx infimium@latest setup

Run setup from the repository you want to index, not from your home directory (~). Infimium stops broad roots automatically so it cannot scan unrelated files.

That creates global config, starts Ollama if it is installed, pulls nomic-embed-text, indexes the current project or workspace, runs doctor, and opens Playground.

The published CLI keeps its executable entrypoint, so MCP clients can launch it directly through the configuration below.

If Ollama is not installed yet:

npx infimium@latest setup --install-deps

infimium setup creates one global config at ~/.infimium/.env. You do not need a .env in every project. Code, docs, memory, graphs, and vectors are stored locally under ~/.infimium/.

Web search is optional. Add a Tinyfish key only when you need it:

SEARCH_PROVIDER=tinyfish
SEARCH_API_KEY=your_key

Full infimium plan generation also needs a local text model:

ollama pull llama3.1

infimium plan --dry-run "your task" works without this model and shows the retrieved code context first.

Connect Your Agent

Cursor, Windsurf, Claude Desktop, and other MCP clients:

{
  "mcpServers": {
    "infimium": {
      "command": "npx",
      "args": ["-y", "infimium", "serve"]
    }
  }
}

Restart the client, then use:

Use Infimium hello_infimium.
Use Infimium get_context before starting.
Use Infimium semantic_code_search to explain this repository.

Infimium normally uses the MCP process working directory. If your client starts it elsewhere, pass project_path once; Infimium remembers the active project and auto-indexes it.

Tools

CLI

Use npx infimium ... if you did not install the package globally.

Project Memory

Refresh memory yourself, or enable periodic checkpoints for the current project:

infimium update --note "Implemented login validation" --task "Finish login" --handoff "Run the auth tests next"
infimium update start --interval 300
infimium update status
infimium update stop

Replace the example notes with your own. Add --project /path/to/repo to select a project and --file src/auth.ts to attach a relevant file. infimium_update and infimium-update are CLI aliases. MCP agents use the infimium_update tool with action: refresh|start|stop|status, project_path, and optional note, task, handoff, files, or interval_seconds.

Auto-update is opt-in and runs while the foreground CLI watcher or an MCP server is open. Its per-project setting survives restarts; stop disables future checkpoints (an in-flight refresh may finish). Checkpoints link episodes, tasks, file references, and handoff notes in local SQLite. Unchanged observations are deduplicated. Automatic checkpoints record observable state, not guessed intent, and never mark a task complete.

get-context / get_context now reads saved context and current memory without rescanning the repo. It includes a bounded memory graph and guidance to answer repo-overview questions only when asked, using Infimium memory first. Missing context is reported explicitly. Run infimium update or get-context --refresh to refresh filesystem context. These are agent guidelines, not an enforcement mechanism for other clients.

Infimium keeps memory bounded across long sessions:

• Scratchpad: recent events for the active task.
• Archive: compact summaries of completed tasks.
• Ledger: durable decisions, rules, quirks, and unresolved blockers.

Record meaningful progress while working:

infimium remember "Added rate-limit middleware" --type progress --task "Rate limiting"
infimium remember "Use Redis-backed counters in production" --type decision

When the task is complete:

infimium memory complete

Infimium uses the local llama3.1 model when available and falls back to deterministic compaction when it is not. Raw compacted events remain stored locally for seven days before pruning. get_context never calls an LLM or network service.

From a source checkout, build once and run the local playground with:

npm run build
npm run playground

Local Architecture

• Ollama creates embeddings on your machine.
• Embedded SQLite stores vectors, index metadata, project memory, and graph edges. No ChromaDB or Docker service is required.
• Documents use recursive boundary-aware chunks instead of blind fixed slices.
• JavaScript, TypeScript, Python, and Dart parsers are bundled.
• Go, Rust, and Java Tree-sitter WASM grammars download on first use and cache in ~/.infimium/grammars/.
• .gitignore, .infimiumignore, and framework defaults exclude dependencies, build output, Flutter artifacts, caches, and binaries before indexing.
• semantic_code_search returns signatures; expand_symbol provides full code on demand.
• Project memory uses session-scoped scratchpads, compact milestone archives, and a versioned semantic ledger.
• get_context emits static anchors, dynamic repository state, and active execution as separate YAML zones.

Multiple Projects

Run the normal index command from a folder containing related projects:

infimium index

Infimium detects immediate project roots from files such as pubspec.yaml, package.json, Cargo.toml, and go.mod. It shows the detected roles and dependencies, asks once, then creates infimium.workspace.json, indexes every project, and opens Playground.

For unattended setup:

infimium index --yes --no-playground

Use --no-workspace to index only the current project. Workspace projects keep separate memory and Git state while get_context includes balanced summaries and graph relationships from related projects.

Infimium - Playground

Infimium drops the initial payload cost from approximately 1,460 tokens to 8 tokens per symbol. Semantic search returns the AST signature first; the agent requests the full implementation only when it needs it with expand_symbol.