Use the docs to get live.
Use the research links when you need claim discipline.
Iranti has two different documentation jobs: help you install and use the system, and help you understand what the current evidence does and does not support. This page keeps those jobs separate so evaluation stays clear.
Quickstart
Install the CLI, bring a database, start an instance, and bind a project.
Claude Code guide
Current MCP and hook setup for Claude Code, including workspace MCP and response-persistence hooks.
Codex guide
Current Codex setup path, including global configuration and VS Code MCP scaffolding.
Manual / operator flow
Use the CLI as an operator surface for status, doctor, repair, lifecycle, and project binding tasks.
Six ideas that explain how Iranti works and why the architecture choices matter.
Entity + key memory
Iranti is strongest when an agent can address the fact it wants directly. That is why entity + key is the core retrieval model.
The Staff
The Library, Librarian, Attendant, Archivist, and Resolutionist divide memory responsibilities into inspectable components with bounded jobs.
Shared versus personal memory
Personal preferences belong on personal entities such as user/main. Project state belongs on project entities. The system now routes those separately.
Conflict and escalation
Deterministic conflicts resolve automatically when the confidence gap is clear. Ambiguous cases should be understood as conservative and escalation-prone.
Recovery and handoff
Iranti helps most when work crosses agent boundaries, process boundaries, or restart boundaries. Explicit retrieval still beats hoping the model remembers.
Operator visibility
Health, doctor, repair, bindings, version drift, and runtime lifecycle are part of the product story, not afterthoughts.
Benchmark highlights, bounded claims, and evaluator notes for the current v0.3.2 release. The right starting point for serious evaluation.
Exact retrieval vs. long-context reading at 2000 entities, ~107k tokens. Null accuracy gap with large token efficiency differential.
Facts written by one agent retrieved by a completely independent process with a different identity. The core persistence guarantee.
Oracle lookups, multi-hop entity chains, and vector-backed search all pass cleanly. The foundation for structured reasoning across a shared KB.
Relationship writes plus one-hop and deep traversal. When work spans people, repos, tasks, and systems, the KB can model those connections.
The evidence pages cover benchmark methodology, trial data, and exact claim boundaries. Start with the overview, then go deeper on individual benchmarks.
Want to try it yourself?
Closed beta is running now. Reach out to request early access and be among the first to run your own workflow on Iranti.