Skip to main content
Contexity sits between your AI coding agent and your project, acting as an intelligent intermediary that delivers only what the agent needs to complete a task. Instead of flooding an agent with a raw memory dump, Contexity assembles a bounded, task-aware context pack — shaped by what you’re working on, what your project graph knows, and how fresh and trusted each piece of context is.

​
Main Pieces

Contexity organizes project knowledge into distinct layers, each serving a specific role in the context pipeline.
PiecePurpose
Project identityConnects a repo checkout to Contexity state
Project intelligenceSource-backed graph and route/project map
Context itemsDurable project notes, decisions, failed attempts, and obligations
External referencesSlack threads, issue comments, docs, repos, and links
External signalsExtracted requirements, decisions, warnings, and research takeaways
Run ledgerRecords what the host did during a task
MetricsHeuristic or benchmark-backed value summaries

​
Normal Agent Flow

Every Contexity-assisted task follows a predictable lifecycle. Your host (the AI agent’s execution environment) drives each step.
1

Start run

Start a Contexity run with the user task. This opens a ledger entry and anchors the session to the current project identity.
2

Retrieve pack

Retrieve the task-relevant context pack before broad exploration or any edits. Contexity selects items based on task text, trust state, freshness, and your token budget.
3

Map impact

When a file or route becomes relevant, ask Contexity for upstream and downstream impact. The project intelligence graph surfaces what else is likely to be affected.
4

Detect changes

After edits, Contexity maps changed files through the project graph and flags any context items that may now be stale or in need of review.
5

Close run

Record used context, validation results, unresolved threads, and metrics. The run ledger captures what actually happened so future tasks can build on it.

​
Why Packs Are Bounded

Context packs are intentionally small. Giving an agent too much context is as harmful as giving it too little — old decisions and noisy notes become hidden instructions that silently steer code in the wrong direction. Contexity selects each pack using:
  • Current task text
  • Task plan hints from the host
  • Source-backed project intelligence
  • Trust state of each context item
  • Freshness state of each context item
  • Stale-file and deletion-tombstone checks
  • Your configured token budget
This combination keeps the agent focused on what is genuinely relevant to the task at hand.

​
Local-First by Default

Contexity is designed to run entirely on your local machine. It does not require cloud authentication for the standard product path. Host setup, MCP serving, project state, and context capsules all operate locally, which means your project context never leaves your machine unless you explicitly configure an external sync.