# Syderial

> Syderial is the system of record for intelligence. Governed continuity for people and agents: where each claim came from, on whose authority, and what the record does not know. These are its developer docs.

- Syderial is a record product, not a memory product.
- What Syderial keeps and serves to a model for each call is the context of record.
- Clients reach Syderial through doors that accept the request formats of OpenAI chat completions, Anthropic messages, OpenAI responses and the Model Context Protocol.
- Syderial issues door addresses and credentials to design partners. Request a briefing at https://syderial.ai/early-access.

## Documentation Sets

- [Abridged documentation](https://syderial.dev/llms-small.txt): a compact version of the documentation for Syderial, with non-essential content removed
- [Complete documentation](https://syderial.dev/llms-full.txt): the full documentation for Syderial

## Notes

- The complete documentation includes all content from the official documentation
- The content is automatically generated from the same source as the official documentation

## Optional

- [Syderial research](https://syderial.ai/research/): Papers and architecture notes.
- [Syderial on GitHub](https://github.com/SyderialAI)
- [Syderial on X](https://x.com/SyderialAI)
- [Syderial on LinkedIn](https://www.linkedin.com/company/124154001/)

## Pages

- [What the record is](https://syderial.dev/overview/): Governed continuity for people and agents: where each claim came from, on whose authority, and what the record does not know.
- [Quickstart](https://syderial.dev/quickstart/): Send a call through a Syderial door with the OpenAI or Anthropic SDK you already use. You change the base URL and add your credential.
- [Coding harnesses](https://syderial.dev/guides/coding-harnesses/): Connect Claude Code or Codex to Syderial. Give the agent the record as MCP tools, send its model calls through a door, or both.
- [The journal](https://syderial.dev/concepts/journal/): Syderial keeps the record as a journal of entries, each dated, signed and posted once. Each line cites its evidence, a correction is a new entry, and the chain of entries is the ledger.
- [Two clocks](https://syderial.dev/concepts/two-clocks/): Every entry keeps two times. Valid time is when a claim applied according to its source. Recorded time is when the record learned it. With both, you can ask what the sources said applied at a time, or what the record knew at a time, without rewriting the past.
- [Labels and information flow](https://syderial.dev/concepts/labels/): Every line and every request has a label. A line reaches a reader only when the reader's clearance dominates its label on every axis, and the same rule governs tool calls.
- [The six stations](https://syderial.dev/concepts/stations/): Capture, Bound, Entail, Compile, Gate and Receipt. Every write and every read passes through the stations in order.
- [Receipts and verification](https://syderial.dev/concepts/receipts/): Every answer, abstention, posting and tool decision gets a signed receipt on an append-only chain. Anyone with the verification key can check the chain without trusting the database that serves queries.
- [Four graphs](https://syderial.dev/concepts/graphs/): Syderial rebuilds four graphs from the journal, one for each question a read must answer. All four come from the journal and nothing else.
- [Doors and credentials](https://syderial.dev/api/): Syderial has four doors. Three accept the request formats of the model APIs your clients already call, and the fourth is an MCP server. All four answer from the same record under the same labels.
- [Chat completions](https://syderial.dev/api/chat-completions/): POST /v1/chat/completions. The OpenAI chat completions format, answered from the record within the caller's clearance.
- [Messages](https://syderial.dev/api/messages/): POST /v1/messages. The Anthropic messages format, answered from the record within the caller's clearance.
- [Responses](https://syderial.dev/api/responses/): POST /v1/responses. The OpenAI responses format, answered from the record within the caller's clearance.
- [Models](https://syderial.dev/api/models/): GET /v1/models. Lists the model aliases configured for your organization, in the OpenAI models list format.
- [MCP door](https://syderial.dev/api/mcp/): The record as Model Context Protocol tools. Agents read the context of record, propose entries and check authority before acting, under the same labels as every other read.
- [Research](https://syderial.dev/research/): Syderial is a research company, and we publish what we find. These papers set out the ideas behind the record.
- [Open source](https://syderial.dev/open-source/): What we intend to open, and in what order. The parts that let anyone check the record without trusting Syderial lead the list.