How it fits in your stack

One call gives your agent the context it needs.

Request

Your sources

  • Google Drive
  • GitHub
  • Slack
  • PostgreSQL
  • +

Verified context

GammaLex doesn'tCarry out the requestMake decisions for your agentChange your source systems

Your rules

You define what a request requires.

A Context Model says what each kind of request must establish, and the rules for settling it. GammaLex checks every run against it.

Example definition
task: summarize_changes_since_last_visitrequires:  - last_visit  - medication_history  - plan_matches_dispensing  - labs_current  - specialist_opinionrules:  freshness: labs are no older than the latest medication change

How it works

  • Define a requestSay what a request requires. Each requirement can be required or optional.
  • Set the rulesDecide how settled it has to be, such as how fresh the evidence must be.
  • Same every runEvery run is checked against it, so the same request gets the same kind of answer.

What it returns

A verdict, the evidence, and what would resolve it.

Before your agent acts, the context engine returns a Context Run, with a Context Manifest inside it: whether the context is enough, what that rests on, and what to do about the rest.

Example Context RunRUN_7D41C2
Outcome
insufficient1 of 5 requirements established · 6 records read
Requirements
  • Last visitEstablished
  • Medication historyNot found
  • Care plan and pharmacy agreeContradictory
  • Recent labsStale
  • Specialist noteRestricted
To resolve
  1. 1Provide Medication change No. 2 (Records system)
  2. 2Confirm which governs: the care plan or the pharmacy record
  3. 3The specialist note is restricted — request access or a summary from the care lead

Context Manifest

The context assembled for this request.

  • Evidence: the information the request depends on, gathered from permitted sources.

  • Context sufficiency: whether the context is enough for the request, and if not, why.

  • Boundaries: what the engine could and could not access.

  • Trace: what it used, and how it reached the result.

Your agent decides what to do next. The context engine doesn't act for it.

SDK

Add it to your Python code.

Your agent keeps its own model and framework; GammaLex handles the context.

python
>>> result = client.context(
      task="summarize_changes_since_last_visit",
      actor="care_agent_prod",
      scope="patient:P-2041",
    )

✓ result.outcome -> insufficient

✓ result.evidence -> 6 records, with provenance

API

Call it from any application.

Send one HTTP request from any stack.

http
POST /v1/context
{
  "task": "summarize_changes_since_last_visit",
  "actor": "care_agent_prod",
  "scope": "patient:P-2041"
}

✓ 200 OK

✓ application/json: a Context Run

MCP

Let your agent use it as a tool.

Your agent calls the context engine like any other tool, inside the framework it already runs in.

agent · mcp
agent › get_context(
          task="summarize_changes_since_last_visit",
          actor="care_agent_prod",
          scope="patient:P-2041"
        )

✓ tool result: a Context Run

✓ the agent reads the outcome before it executes

CLI

Run it on your machine.

Work with the context engine from your own machine.

zsh
$ gammx run --bundle <bundle> \
    --task summarize_changes_since_last_visit \
    --actor care_agent_prod \
    --scope patient:P-2041

✓ Context Run written

✓ outcome: insufficient