Skip to main content
Glama

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.

npm version MCP Badge MIT GitHub stars

Demo

Infimium demo

Related MCP server: LocalNest MCP

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

Tool

What it does

hello_infimium

Confirms the MCP server is healthy.

get_context

Reads saved YAML repo context, current memory and handoff; explicit refresh updates Git/index state.

infimium_update

Refreshes episodic memory and handoff graphs; controls automatic memory checkpoints.

semantic_code_search

Finds code by meaning and returns symbol signatures first.

expand_symbol

Loads one full implementation only when needed.

query_local_docs

Searches local Markdown, text, HTML, and PDF files.

dep_graph

Shows imports, callers, callees, and HTTP routes for a symbol.

project_memory

Keeps active scratchpad events, compact milestones, and durable project rules across agents.

plan

Builds a grounded implementation plan from code and graph context.

web_search

Searches the web through optional Tinyfish configuration.

fetch_url

Extracts readable Markdown or text from a URL.

shell

Runs allowlisted commands with timeouts and output limits.

CLI

Command

Description

infimium doctor

Run health checks on your dependencies and setup.

infimium status

Show the current status of the index and memory.

infimium --help

Shows all relevant cli commands.

infimium playground

Launch the local web UI to explore index, graph, and memory.

infimium index

Scan and index the current project directory (code, docs, dependencies).

infimium watch

Run the indexer in watch mode to continuously index changes.

infimium get-context

Output the full flattened context as YAML (layer.md).

infimium code-search <query>

Semantically search code and return symbol signatures.

infimium expand-symbol <symbol>

Fetch the full implementation code for a specific symbol.

infimium docs-search <query>

Semantically search local markdown/text documentation.

infimium dep-graph <symbol>

Show dependencies, callers, callees, and route graph.

infimium plan --dry-run "<task>"

Draft an implementation plan based on a given prompt.

infimium remember "<note>"

Add a milestone, progress, or decision to project memory.

infimium resume

Show the active task and recent scratchpad memory events.

infimium memory complete

Compact the active scratchpad into an archived milestone.

infimium memory search "<query>"

Semantically search past project rules and memory ledger.

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.

Full implementation   ~1,460 tokens
AST skeleton               ~8 tokens
Initial payload reduction  ~99.5%

These are Playground reference values, not a claim that every function has the same size. Inspect your own indexed repository and compare AST-first retrieval with full-text retrieval locally:

infimium playground

Open Token Economics to see the estimated token difference across your actual indexed symbols.

Privacy

Code, docs, embeddings, memory, graph data, prompts, queries, file paths, and repo names remain local.

Infimium sends privacy-safe anonymous lifecycle telemetry so we can understand setup success:

  • init_started, init_completed

  • doctor_run, doctor_passed

  • index_started, index_completed, setup_completed

  • serve_started, first_tool_call, playground_opened

Telemetry includes an anonymous install ID, Infimium version, OS, Node major version, timestamp, and event name. It never includes code, file paths, repo names, prompts, search queries, memory notes, API keys, or user identity.

Disable it anytime:

infimium telemetry off

or set:

INFIMIUM_TELEMETRY=false

Troubleshooting

FAQ & Common Confusions

Where is layer.md? When you run infimium get-context, it prints saved context directly to your terminal (stdout). Refreshes store project-scoped YAML under Infimium's local data directory. To export the saved context to a file, use terminal redirection:

infimium get-context > layer.md

Why does the Playground UI say "Awaiting first agent interaction..."? The CURRENT TASK tracker reflects stored project context. Run infimium update --task "Your task" to refresh it; get-context reads the saved snapshot.

How do I format infimium remember? The infimium remember command requires a message and a --type flag (valid types: note, progress, decision, blocker, index, plan). If you also want it to update the active task in the Playground, include the --task flag:

infimium remember "Added rate limiting" --type progress --task "Security Features"

Database is locked

If you see Failed to start Infimium: Database is locked, it means another instance of Infimium is actively holding a lock on the SQLite memory database. This usually happens if you try to run infimium index manually in one terminal while infimium playground or infimium watch is still running in another. Simply stop the running process (Ctrl+C) before running manual commands.

General Setup Issues

Run:

infimium doctor

Every failed check prints one copy-paste fix. If setup still fails, give this prompt to your coding agent:

Set up Infimium in this repository. Install/start Ollama, pull nomic-embed-text,
run npx infimium init, run npx infimium index, and make all six
npx infimium doctor checks pass. Do not commit secrets.

Contributing

See CONTRIBUTING.md. Adding a language starts with a parser fixture and extraction test.

Self-hosting is free forever under the MIT license.

Available Tools

11 tools
dep_graphC

Inspect dependency relationships for a symbol.

Inputs: symbol_name (required), project_path.

expand_symbolB

Load the full implementation of one symbol returned by semantic_code_search.

Inputs: symbol_name (required), file_path, project_path.

fetch_urlC

Fetch a URL and extract readable content.

Inputs: url (required), extract.

get_contextA

Read the balanced YAML context layer with repo overview, Git state, task, memory, and AST-first handoff guidance. Pass project_path once to activate the current IDE workspace as the default.

Inputs: limit, format, refresh, project_path.

hello_infimiumB

Health probe for the Infimium MCP server.

Inputs: no named parameters.

planC

Generate a grounded implementation plan for the current repository.

Inputs: task (required), top_k, dry_run, language, +3 more.

project_memoryB

Manage compact project memory across chats, agents, and IDEs: remember active work, complete and archive sessions, search history, or update durable rules.

Inputs: key, note, task, limit, +7 more.

query_local_docsC

Query indexed local documentation.

Inputs: query (required), top_k, project_path.

shellC

Run an allowlisted shell command.

Inputs: command (required), cwd, timeout.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3/5.0

    Scored across 11 tools

    Disambiguation5/5

    Each tool targets a clearly distinct function: context reading, health probe, web search, URL fetching, local docs, semantic code search, symbol expansion, dependency graph, shell execution, planning, and project memory. There is no overlap or ambiguity between them.

    Naming Consistency2/5

    Naming is inconsistent: some tools use verb_noun (web_search, fetch_url, expand_symbol), while others are bare nouns (shell, plan), abbreviations (dep_graph), or greetings (hello_infimium). This mixed style makes the set harder to predict and navigate.

    Tool Count5/5

    With 11 tools, the server is well-scoped—each tool earns its place and the count is within the ideal 3-15 range. It feels comprehensive without being bloated.

    Completeness4/5

    The tool surface covers a broad workflow: context, code exploration, web/docs lookup, shell access, planning, and memory. Slight gaps like a direct file editor exist, but shell can fill in, so the coverage is nearly complete.

    Maintenance

    ActivityStale
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server for semantic code search & navigation that helps AI agents work efficiently without burning through costly tokens. Instead of reading entire files, agents can search conceptually and jump directly to the specific functions, classes, and code chunks they need.
      122
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      A local-first MCP server that provides AI agents with safe codebase access through file discovery, hybrid lexical-semantic search, and project introspection. It features durable local memory and semantic indexing while keeping all data and processing entirely on your local machine.
      74
      27 npm
      6
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that gives AI agents structured code understanding and precise code intelligence via local indexing of AST, call graphs, and semantic search.
      73 npm
      4
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that provides structure-aware code analysis (symbol trees, dependencies, docs) to reduce AI agent token consumption by up to 99%, along with Git commit intelligence.
      MIT