Chrysent Axis Code

The problem this solves

Coding assistants burn tokens searching the same repository again and again. They re-index on every session, lose the call graph, and miss the files that actually matter for the task.

You need a shared semantic index and code graph that lives once, is queried many times, and respects repository permissions.

What changes when you adopt Axis Code

• Persistent semantic index

  Index once, reuse across all coding sessions — no per-session indexing cost, no lost context.

• Call graph and dependency navigation

  Trace relationships between symbols and files. Coding agents land on the right starting point faster.

• Token efficiency for AI sessions

  Coding agents retrieve precisely the files and symbols they need rather than dumping a context window.

• MCP and CLI access

  Axis Code exposes its index over MCP and a CLI so your existing tooling integrates without rewrites.

How Axis Code operates

1. 01

   Index a repository

   Run the Axis Code indexer on a repository or branch. The graph is built once and reused.

2. 02

   Connect your coding agent

   Coding agents access the graph via MCP or CLI. The agent asks for the relevant files; Axis returns precisely them.

3. 03

   Maintain the index

   Branch-level diffs re-index incrementally. The main codebase stays warm.

Component map

• IndexPersistent semantic and call-graph index per repository.
• MCP serverExposes search and navigation to any MCP-compatible agent.
• CLILocal integration for human engineers and CI hooks.

For the full platform architecture, see /platform.

Who uses it and how

• Engineering leadership

  Scenario: You want to adopt coding agents without ballooning token costs.

  Gain: A shared semantic index that cuts retrieval cost and improves accuracy.

• Platform engineering

  Scenario: Your developers want a single search surface for unfamiliar codebases.

  Gain: Semantic and full-text search across the indexed repository with call-graph navigation.

See the product surface

Supported systems

Chrysent Axis Code integrates with the providers and frameworks below. Each entry shows the current support status. Documentation for the full integration list is coming soon.

• Model Context Protocol (MCP)Generally available
• CLIGenerally available
• 300+ languages supportedGenerally available

Where it runs and how data is handled

Chrysent sells self-hosted software only. Software and retained product data remain in customer-owned or customer-controlled infrastructure. Customer-configured external model providers receive provider-bound request data under the customer's provider agreement. This model supports data sovereignty and residency requirements. Data handling and retention are described on the Data handling & deployment page. Security architecture, encryption, and incident response are documented on Security & trust.

Benchmark and evaluation methodology

The first public benchmark study is in preparation. Until it ships, design partners can request the evaluation methodology and a private run report under NDA via the contact form.

Other Chrysent products

• Chrysent AI Gateway

  Private beta

  Chrysent AI Gateway provides centralized control over AI usage across multiple vendors and models.

• Chrysent Touchstone

  Private beta

  Chrysent Touchstone focuses on protecting AI systems from malicious or unsafe interactions.

• Chrysent Axis Knowledge Base

  Design-partner preview

  Axis Knowledge Base turns your institutional knowledge into actionable intelligence.

Common questions

• How is the index kept current?

  The main codebase is re-indexed on a schedule; branch-level diffs are indexed incrementally.

• What languages are supported?

  See the published language list under /docs. The list is updated with each Axis Code release and is dated.

• How is access controlled?

  Index access follows repository permissions. Cross-tenant access requires explicit configuration.