# Context for agents · Neural Inverse Govern > Spaces of code, issues and team knowledge that follow your organisation, served to the Editor, the Agents app, the CLI and MCP clients with authorisation, DLP and a token budget, and recorded as evidence. Source: https://neuralinverse.com/govern/context/ --- ![](/photos/team.jpg) [Neural Inverse Govern / Context for agents](https://neuralinverse.com/govern/) # Agents work from approved knowledge, checked for the person asking on every retrieval. Spaces of code, issues and team knowledge that follow your organisation, served to the Editor, the Agents app, the CLI and MCP clients with authorisation, DLP and a token budget, and recorded as evidence. Sources GitHub code and issues, personal documents Classification Four levels, tighten only Served to Editor, Agents app, CLI and MCP clients Evidence HMAC-chained attribution Runs Inside Govern, on PostgreSQL Overview The Context Platform decides what context an AI tool may see. It indexes repositories, issues and team knowledge into spaces that follow your organisation's structure, and answers every retrieval through the same fixed steps: authorise each space for the person asking, search, rank, apply DLP by classification, cut to a token budget, and record exactly which chunks were delivered. [What it does ↓](https://neuralinverse.com/#capabilities)[How it works ↓](https://neuralinverse.com/#workflow)[Enforced and recorded ↓](https://neuralinverse.com/#enforcement)[Where it runs ↓](https://neuralinverse.com/#where)[Get started ↓](https://neuralinverse.com/#get-started) What it does ## What the Context Platform does. Governed retrieval for every AI tool, and the shared knowledge teams build around it. - **Spaces that follow your organisation:** One space for every organisation, department, team, group and project, kept in step with your directory. A deleted node's space is archived, never deleted. - **GitHub through your own App:** Repositories and issues are read through a GitHub App your organisation owns, with read-only permissions and tokens limited to one repository. Personal access tokens are not accepted. - **Indexing:** Versioned, re-run on push and caught up by a maintenance scan. Environment, secret, key and credential files are skipped by path before any content is read, so they are never stored. - **Authorisation on every retrieval:** Each space is checked for the person asking before anything is searched: organisation deny rules, the role grant and membership by classification. Restricted spaces are readable by their own members only, with no administrator override. - **Classification and DLP:** Four levels, inherited from the strictest ancestor and only ever raised. Findings are redacted at public and internal, dropped at confidential, and withhold the whole source at restricted; regulated projects get at least drop. - **Embeddings behind DLP:** Vector search is optional. Confidential and restricted sources are never sent to an external embeddings endpoint, and every other chunk is redacted before it is embedded. - **Attribution:** Every retrieval is recorded with the person, the spaces, the sources and a SHA-256 of every chunk delivered, in an HMAC-chained evidence record verified daily. - **Linked to the model call:** When the Neural Inverse apps call a model through the AI Gateway, they name the retrieval they used, and the link is appended to the same evidence chain. - **Lenses:** Saved selections of sources that people share at view, use or edit level, with expiry and approval above a classification line. Sharing a lens never grants access to content. - **Snapshots and handoffs:** Immutable snapshots of retrieved context, handed to the reviewers of a pull request and shown through each reviewer's own authorisation. - **Pair sessions:** Invite-only live sessions that retrieve through one shared lens, with a recording of the retrievals made in them. - **Team memory:** Decisions, conventions, notes and glossary entries a team edits together. Only text another member reviewed and accepted reaches the AI. - **Work registry:** Who is changing what in each repository, and where two pieces of work overlap. Advisory only, and it holds names, never code or content. - **Agent instruction files:** CLAUDE.md, AGENTS.md and similar files kept in organisation, team, project and personal layers, with versions, approval, rollback and legal hold, and a record of which versions each agent session started with. - **Collaboration policy:** Switches and limits for sharing, handoffs, pair sessions, team memory and agent files per organisation, department, team and project, with a classification ceiling and share expiry. Lower levels only tighten. - **MCP endpoint and live feed:** MCP clients retrieve through the same steps as the person signed in. The Neural Inverse apps follow changes through an ordered event feed that carries ids, never content. Source connectors exist for GitHub repositories, issues and pull requests, and personal documents; wikis, documentation systems and conversations are not available yet. The collaboration policy, team memory, the work registry and agent instruction files have no console page yet; they are used from the Neural Inverse apps and the API. How it works ## How a retrieval is answered. Every retrieval takes the same steps, whether it comes from an app, an MCP client, a lens or the endpoint agent. A failure at any step fails the request closed. 1. Candidates The spaces that can contribute: the project's chain and the caller's own teams and groups. 2. Authorise Each space is checked for the caller. Spaces that fail are dropped before anything is searched. 3. Search Full-text, and vector search where configured, over the authorised spaces only. 4. Rank A hybrid score, weighted by the level of the space the chunk came from. 5. Protect The DLP action of each source's classification is applied to every chunk. 6. Budget Chunks are added in rank order until the token budget is used. 7. Attribute The request, spaces, sources and a hash of every chunk go to the evidence chain. Who uses it ## Built for every role that answers for AI. - **Platform administrators:** Connect the GitHub App, add sources, set classifications and organisation deny rules. - **Security and compliance teams:** Set collaboration policy and ceilings, oversee and revoke shares, and read attribution records. - **Engineers:** Get governed context in the Editor, the Agents app and the CLI; share lenses and hand context to reviewers. - **Team leads:** Accept team memory entries and see where their team's work overlaps with another's. Enforced and recorded ## What is checked on every request, and what is advisory. Access to context is enforced by the server for each person. Some features only inform; they say so. Enforced - **Per-space authorisation:** On retrieval, lenses, snapshots, handoffs, pair sessions and the MCP endpoint. A database error fails closed, and an object the caller may not read answers like one that never existed. - **Deny rules:** Organisation deny rules refuse Context actions on chosen nodes for everyone, super admins included. - **Classification:** DLP by level, tighten-only values, and frozen content re-scanned at the stricter of its captured and current level. - **Decisions by people:** Approving an agent file version, setting a legal hold, accepting team memory, sharing a lens and acknowledging an overlap refuse API keys. Nobody approves their own. - **Secret files:** A built-in deny list of environment, key and credential files applies to indexing, agent files and shares. No policy can remove it. Recorded - **Retrievals:** Every retrieval and every model call linked to it, with the verified OAuth client. The app name an app declares is recorded, never trusted. - **Agent sessions:** The exact set of instruction files an agent session started with. - **Policy and shares:** Every collaboration policy version, immutable, with author and reason; every share revocation with its reason. - **Work registry:** Advisory only: it never blocks work. The first acknowledgement of an overlap by a person is an audit entry. Where it runs ## Inside Govern, with no external service. [Deployment options](https://neuralinverse.com/deployment/) - **PostgreSQL only:** Spaces, sources, chunks and the event feed are held in PostgreSQL. No message broker is needed. - **Embeddings optional:** Full-text search works on its own. An embeddings endpoint inside your deployment adds vector search. - **GitHub Enterprise:** Your own GitHub host can be added to the hosts the connector accepts. - **Hosted by us:** We run it for you, with the same controls and audit record. Get started ## Set it up with the documentation. - [Context Platform](https://neuralinverse.com/docs/context/) - [Spaces and sources](https://neuralinverse.com/docs/context/spaces-and-sources/) - [Classification and deny rules](https://neuralinverse.com/docs/context/classification/) - [Retrieval and attribution](https://neuralinverse.com/docs/context/retrieval/) - [Lenses and sharing](https://neuralinverse.com/docs/context/lenses/) - [Handoffs, snapshots and pair sessions](https://neuralinverse.com/docs/context/handoffs-and-pair-sessions/) - [Collaboration policy](https://neuralinverse.com/docs/context/collaboration-policy/) - [Team memory](https://neuralinverse.com/docs/context/team-memory/) - [Work registry](https://neuralinverse.com/docs/context/work-registry/) - [Agent instruction files](https://neuralinverse.com/docs/context/agent-files/) - [MCP endpoint](https://neuralinverse.com/docs/context/mcp/) Related [AI Gateway → Approved models, DLP, guardrails, budgets and rate limits for every model request.](https://neuralinverse.com/govern/ai-gateway/)[Audit and evidence → A hash-chained audit log you can verify offline, and evidence toward your frameworks.](https://neuralinverse.com/govern/audit/)[Identity and access → Single sign-on, provisioning, least-privilege roles, just-in-time access and reviews.](https://neuralinverse.com/govern/identity/) ![](/photos/team.jpg) ## Talk to our team. Neural Inverse is available by request. We work with your engineering, security and procurement teams from the first conversation. [Request access](https://neuralinverse.com/contact/?topic=access)[Contact us](https://neuralinverse.com/contact/)