The open access and governance layer for AI agents across your organization.
Give every agent the right organizational context through one identity and policy model, with provenance, audit, and signed erasure.
As AI spreads across an organization, every agent needs access to shared
context without becoming its own identity system, policy engine, or audit silo.
Halofy sits between organizational knowledge and the agents that use it. It
resolves identity, enforces access, governs change, records every outcome, and
makes erasure independently verifiable.
Underneath that governance boundary, Halofy maintains durable context and keeps
retrieval replaceable. The result is infrastructure you can inspect, self-host,
run offline, and connect to any agent over MCP or HTTP.
Why Halofy
Organization-wide access
Governed context
Open infrastructure
Agents, applications, and operators use the same server-resolved identity, namespace ACL, roles, and policy boundary over MCP or HTTP.
Every change follows one auditable path with provenance, supersedence, append-only history, and signed erasure.
Postgres remains the authority while retrieval engines plug in through an ACL-scoped, read-only driver interface.
What ships in this repository
One governed access surface over MCP and HTTP:mem_write, mem_read, mem_search,
mem_assemble, mem_fault, mem_stats, mem_forget, policy, sharing,
pinning, export, and manifest operations.
Organization-wide identity and access control: credentials resolve actor,
role, namespace, and source scope server-side before any read or write.
A governed context lifecycle: provenance, entity resolution, exact and
semantic dedupe, supersedence chains, and append-only audit.
One organizational authority across two tiers: Postgres/pgvector for
operational context and encrypted, Git-versioned knowledge for the cold tier.
Embedded PGlite is the zero-setup local default.
A frameworkless control room: access, teams, sources, policies, conflicts,
retrieval quality, audit, alerts, skills, connected apps, and export.
Four public connectors: filesystem, Postgres, Obsidian, and manual CSV
import. All feed the same governed write path.
A hermetic test lane: embedded PGlite, deterministic StubLlm,
HashEmbedder, and zero network access.
Quickstart
Run the complete offline story
git clone https://github.com/halofyai/halofy.git
cd halofy/kernel
npm ci
npm run demo
No API key. No database server. No model download. No network call. The demo
boots the real kernel on embedded PGlite, then exercises pinning, assembly,
writes, hybrid search, an L3 context fault, audit, import, fragmentation, and
signed erasure.
== T0 ·· boot in-memory, pin the refund policy, assemble the working set
booted: embedder=hash(dim=256) llm=stub
== T3 ·· mem_fault - page missing context in from L3
fault: hit=true source=L3 injected=2
== T7 ·· mem.forget - erase the customer and mint a signed certificate
certificate 01... verifyCertificate === true
after forget: mem_search surfaces 0 matching facts
demo complete - kernel closed.
Then prove the kernel and its retrieval boundary:
npm test
npx tsx src/cli.ts conformance baseline
The current standalone verification passes 2,678 tests across 205 files and
all 6/6 driver-conformance checks. Timings and generated identifiers vary by
machine; the behavior does not.
cd kernel
npx tsx src/cli.ts keygen org/support/agent-1 user:dana owner
HALOMEM_API_KEY=hm_... npm run mcp
The API key resolves the namespace, actor, and role server-side. MCP tool
schemas do not accept caller-asserted identity fields.
Architecture
The important boundaries
Identity is server-owned. Namespace, actor, role, and source scope come
from the credential, never from a request body.
Access is organization-wide and policy-bound. The same ACL and role
decisions apply across agents, applications, operators, MCP, and HTTP.
Changes are governed. Corrections close the prior fact's validity interval
and link the replacement. They do not overwrite history.
Reads are delegated. A retriever sees only an ACL-scoped ScopedView and
can return references only. It cannot write or reach audit/storage modules.
Postgres is the authority. Context, embeddings, policy, provenance,
tombstones, and audit live together. PGlite embeds the same model for local
development and tests.
Every outcome audits. Success, denial, miss, brownout, and error paths all
append an event.
Read the architecture guide for the syscall pipeline,
ACL examples, SQL, tiering, brownout behavior, and a per-directory source map.
Security model
The core namespace rule is deliberately small: a caller in namespace N sees
rows belonging to N or an exact /-split ancestor of N. Siblings and
descendants remain invisible unless an explicit, audited administration path
allows a subtree operation.
The query layer enforces this rule with exact ancestor matching. Retrieval
drivers do not reimplement it; they receive an already-scoped view. See the
threat model for the known partial controls and
adversarial cases, and the architecture guide for the
worked ACL queries.
Open by design
The standalone build is not a trial:
Property
Standalone behavior
Licence/activation
No licence key, edition flag, activation, or entitlement check
Packaging quota
None; the public QuotaPort defaults to UNMETERED
Capacity controls
Operator-owned policy rate limits and model-budget brownout only
Telemetry
None; no usage beacon or Halofy phone-home
Models
Offline deterministic defaults; optional direct Anthropic, OpenAI-compatible, OpenAI embedding, and Azure OpenAI configuration
Database
Embedded PGlite by default; regular Postgres/pgvector for durable deployments
Halofy's managed operations, not the access and governance boundary, fund the
open kernel:
model routing, spend attribution, and gateway observability;
billing, credit ledger, and hosted usage plans;
operated Slack, Discord, WhatsApp, and Google Chat applications;
the managed SaaS connector catalogue and its OAuth applications;
federated live query across organizations;
the tuned extraction prompt pack; and
managed infrastructure, upgrades, backups, uptime, and support commitments.
None of those components is required to run this repository. The connector
framework, baseline model plumbing, governed context lifecycle, access control,
console, self-host stack, and test suite are present and runnable.
Start with CONTRIBUTING.md. Security-sensitive changes to
authentication, tenancy, ACLs, migrations, encryption, audit, erasure, or the
write/retrieval boundary require adversarial review and regression coverage.
Security reports belong in the private channels described by
SECURITY.md, not in public issues. Community expectations are in
CODE_OF_CONDUCT.md.
License
The kernel and console are AGPL-3.0-or-later. Named client and extension
subtrees are Apache-2.0 so they can be embedded without relicensing the
host application. These include kernel/src/driver/, kernel/src/mcp/, and
kernel/integrations/. See LICENSING.md and NOTICE
for the authoritative file-by-file boundary.
The Halofy name is a trademark; neither software licence grants trademark
rights. See TRADEMARK.md.
