agentic-codebase 0.1.0

Standalone guarantee: AgenticCodebase is independently installable and operable. Integration with AgenticMemory/AgenticVision is optional, never required.

Autonomic defaults (phase 4): profile-driven operations (ACB_AUTONOMIC_PROFILE = desktop|cloud|aggressive) now control backup/maintenance posture, while compile keeps rolling output backups and collective cache self-maintenance active by default. Storage migration is policy-gated (ACB_STORAGE_MIGRATION_POLICY = auto-safe|strict|off) with checkpointed auto-safe behavior. SLA-aware collective maintenance throttling is enabled (ACB_SLA_MAX_REGISTRY_OPS_PER_MIN) plus health-ledger snapshots (ACB_HEALTH_LEDGER_DIR or AGENTRA_HEALTH_LEDGER_DIR) for CLI and collective surfaces. Default ledger location is ~/.agentra/health-ledger. Optional tuning: ACB_AUTO_BACKUP, ACB_AUTO_BACKUP_RETENTION, ACB_AUTO_BACKUP_DIR, ACB_COLLECTIVE_CACHE_MAINTENANCE_SECS, ACB_HEALTH_LEDGER_EMIT_SECS.

AI agents can't understand code across sessions.

Your agent reads a file, analyzes one function, and forgets. Next session -- blank slate. It can't recall the architecture it mapped yesterday. It can't trace the impact chain from three conversations ago. It can't search its own understanding of your codebase.

RAG over source files doesn't work. You get "similar text," never "what breaks if I change this?". Embedding chunks loses all structure -- no call graphs, no dependency chains, no type relationships. Grep is fast but flat.

AgenticCodebase compiles your repository into a navigable concept graph stored in a single binary file. Not "search your source code." Your agent has a map -- functions, classes, modules, imports, call chains, type hierarchies -- all connected, all queryable in microseconds.

# Compile any repository (Python, Rust, TypeScript, Go)
acb compile ./my-project -o project.acb

# Query it
acb query project.acb symbol --name "UserService"     # Find symbols
acb query project.acb impact --unit-id 42              # What breaks?
acb query project.acb prophecy --limit 10              # What will break next?

Four languages. Twenty-four query types. One file holds everything. Sub-microsecond lookups. Works with Claude Desktop, VS Code, Cursor, Windsurf, and any MCP-compatible client.

Benchmarks

Rust core. Tree-sitter parsing. Binary .acb format. Real numbers from cargo bench --release:

All benchmarks on Apple M4 Pro, macOS, Rust 1.90.0 --release. Criterion 0.5 with 100 iterations after warm-up.

Why AgenticCodebase?

Quickstart

Install

cargo install agentic-codebase

Compile a codebase

# Parse and compile a repository into a .acb graph
acb compile ./my-project -o project.acb

# View graph metadata
acb info project.acb

# Query symbols
acb query project.acb symbol --name "UserService"

# Impact analysis -- what breaks if I change unit 42?
acb query project.acb impact --unit-id 42 --depth 5

# Code prophecy -- what's likely to break next?
acb query project.acb prophecy --limit 10

MCP Server

# Start the MCP server (stdio transport)
acb-mcp

Configure in Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "agentic-codebase": {
      "command": "acb-mcp",
      "args": []
    }
  }
}

See the Full Install Guide for VS Code, Cursor, and Windsurf configuration.

The Query Engine

AgenticCodebase provides 24 query types across three tiers:

Core Queries (8)

Built Queries (5)

Novel Queries (11)

Architecture

AgenticCodebase models source code as a directed graph G = (U, E) where each vertex is a typed CodeUnit and each edge carries a semantic relationship.

Compilation Pipeline

Source Files (Py/Rust/TS/Go)
    -> tree-sitter Parse
    -> Semantic Analysis
    -> Graph Builder
    -> .acb Binary

Binary Format (.acb)

Code Unit Types (13)

Function, Method, Class, Struct, Enum, Interface, Trait, Module, Import, Variable, Constant, TypeAlias, Macro

Edge Types (18)

Calls, CalledBy, Imports, ImportedBy, Contains, ContainedBy, Inherits, InheritedBy, Implements, ImplementedBy, Uses, UsedBy, Returns, Accepts, Overrides, OverriddenBy, Tests, TestedBy

Install

cargo install agentic-codebase

See the Full Installation Guide for all options including MCP server setup, library usage, and build-from-source instructions.

Integration with Agentic Ecosystem

AgenticCodebase is part of the Agentic ecosystem:

• AgenticMemory -- Persistent, navigable memory for AI agents
• AgenticVision -- Visual memory and image understanding for AI agents
• AgenticCodebase -- Semantic code understanding for AI agents

All three share the MCP protocol for seamless AI agent integration. Run all three servers together for an agent with memory, vision, and code understanding.

Implementation

• Language: Rust
• Source files: 58
• Lines of code: 13,709
• Tests: 432 (38 unit + 394 integration)
• Benchmarks: 21 Criterion benchmarks
• Clippy warnings: 0
• Supported languages: Python, Rust, TypeScript, Go

Contributing

See CONTRIBUTING.md for development setup and guidelines.

License

MIT -- see LICENSE for details.