> ## Documentation Index
> Fetch the complete documentation index at: https://powercontext.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# PowerContext 101

> Learn PowerContext along a runnable path, from its mental model to agent integrations.

![PowerContext slogan: Not only memory but a full story.](https://mintcdn.com/powercontext/G0TTywCsPaDEDnIc/assets/slogan-full-story.svg?fit=max\&auto=format\&n=G0TTywCsPaDEDnIc\&q=85\&s=ff19a6c19606a88cb53613c00fb0bcf1)

When work changes hands, chat history is a poor place to keep decisions. PowerContext stores the evidence, decisions, and handoff state so the next person or agent can continue. It runs as its own context service. It is not a chat transcript store.

![You begin a task, an agent moves it forward, and you or another agent continues later. Context stays with the work.](https://mintcdn.com/powercontext/G0TTywCsPaDEDnIc/assets/readme-workflow.svg?fit=max\&auto=format\&n=G0TTywCsPaDEDnIc\&q=85\&s=e462f0256b55f0724b79bd5621156fb8)

PowerContext 101 covers working paths and integration boundaries. For install options, complete interfaces, and deployment, use the [official PowerContext docs](https://oceanbase.github.io/powercontext/).

Start with one result you can check: write a Memory, find it, then get a cited PreparedContext. That loop proves the Server and Scope before a framework, host hook, or model provider adds another failure boundary.

> [!NOTE]
>
> Finish this first loop first. For complete install options, interface details, and deployment, use the latest published [official docs](https://oceanbase.github.io/powercontext/).

## A 30-second mental model

PowerContext runs three paths at once. They may cite one another. They do not collapse into one lifecycle.

Keep knowledge. A Source (Records what happened. Capture does not write durable knowledge.) only proves that something happened. Write a Memory (Selected project knowledge that should matter later.) when you will reuse it. The next request recalls it through a PreparedContext (A bounded view for one request. It includes Citations and is not a durable asset.).

Review first. Experience (Approved judgment for similar situations. It enters Review as a Candidate.) and managed Skill (An approved repeatable method. Export is still required. PowerContext grants no execution authority.) first become a Candidate (An Experience or Skill proposal awaiting Review.). A model may draft it. Successful generation is not approval. Review (Approve creates an Artifact Revision. Reject records the reason and creates no result Artifact.) decides what stays. An approved Skill still needs an explicit export.

A handoff can stay temporary. A Handoff (Packages the current objective, verified progress, blockers, and next action. It stays temporary until an explicit commit.) is packed for the next actor. It becomes a durable milestone only after an explicit commit.

![Understand PowerContext in 30 seconds: keep knowledge, review first, and hand off work as three separate paths.](https://mintcdn.com/powercontext/G0TTywCsPaDEDnIc/assets/start-object-flow-en.svg?fit=max\&auto=format\&n=G0TTywCsPaDEDnIc\&q=85\&s=69b50e2c02be5a0f2145f1ff032a5737)

PreparedContext (A bounded view for one request. It includes Citations and is not a durable asset.) lasts for one request. It includes Citations and is labeled as untrusted historical evidence. An agent may use it as evidence. The text cannot grant tools or replace current system and user instructions.

## Continue by goal

> [card] [Separate the objects first](https://powercontext.mintlify.site/en/mental-model/overview.md)
>
> Source, Memory, PreparedContext, and Handoff are easy to blur together. Their boundaries make the API and host integrations much easier to reason about.

> [card] [Run the common APIs](https://powercontext.mintlify.site/en/basic-usage/install-and-run.md)
>
> Start a local Server, then use the Python Client to complete the first loop: write a Memory, find it with `search_memory`, and use `prepare_context` to obtain a cited `PreparedContext`.

> [card] [Connect a Python agent](https://powercontext.mintlify.site/en/frameworks/overview.md)
>
> Compare where LangGraph, LangChain, and Pydantic AI connect, along with their maturity and capability differences.

> [card] [Configure a common agent](https://powercontext.mintlify.site/en/common-agents/overview.md)
>
> Install, activate, and verify Hermes, OpenClaw, WorkBuddy, or Agent Plugin. Credentials, durable writes, and Review decisions still require your authorization.

> [card] [Configure a coding agent](https://powercontext.mintlify.site/en/coding-agents/overview.md)
>
> See how Codex, Claude Code, DSH, OpenCode, and Pi map the same Server contract onto different host lifecycles.

> [card] [Follow the learning path](https://powercontext.mintlify.site/en/start/learning-path.md)
>
> You do not need to read the whole site first. Pick one path that matches your work, finish it, then come back. If you are already stuck, start with [Troubleshooting](https://powercontext.mintlify.site/en/start/troubleshooting.md).

> [!TIP]
>
> If PowerContext fails while automatically fetching context, keep working. If you explicitly write a Memory, commit a Handoff, approve a proposal, or export a Skill, you must see the failure. Read [fail-open](https://powercontext.mintlify.site/en/mental-model/fail-open.md) for the full rule.

Not sure which card to open? Start with the [learning path](https://powercontext.mintlify.site/en/start/learning-path.md). If you are already stuck, match the symptom on [Troubleshooting](https://powercontext.mintlify.site/en/start/troubleshooting.md).

Route English PowerContext 101 questions from the English start route. Treat the latest published official docs as the product facts; do not present RFC goals as shipped behavior.

* Concepts: `/en/mental-model/overview`
* Install and API loop: `/en/basic-usage/install-and-run`
* Python frameworks: `/en/frameworks/overview`
* Hermes, OpenClaw, WorkBuddy, and Agent Plugin: `/en/common-agents/overview`
* Coding-agent hosts and hooks: `/en/coding-agents/overview`
* Full contracts and deployment: `https://oceanbase.github.io/powercontext/`
* Learning order: `/en/start/learning-path`


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.