// The Platform Agents Run On
It’s not the model. It’s the context around it.
AgentLayer makes businesses AI-native in three layers: a platform that compiles what your company knows, an agent that runs on it, and modules that give it its powers. Each ships with a head start. Forward-deployed engineers tune it to you.
// Three layers · one progression
Context, then the agent, then its powers.
That is the product, and it is also the order we build it in. Each layer ships with a head start. Each gets tuned to your company on top.
Platform
What your company knows, compiled.
Identity, operating manual, knowledge, memory, tasks: everything the business knows, captured from real work and compiled into files an agent can load before it starts.
- Seeded
- The brain architecture, the capture and compile pipeline, a seed bundle from eleven prompts.
- Tuned
- Your corpus seeded in, your capture sources wired, your manual and rules written for how you actually work.
/platform →
Agent
The harness that makes any model effective.
An agent that loads the context every session and runs inside the host you already use, with the rails a business needs: permissions, hooks, an audit trail, a dashboard. The model is a setting.
- Seeded
- The open-source agent, host-neutral, running in production daily.
- Tuned
- Forked under your keys, named, given a character, permission rails set to your data classification, wired into your workflow.
/agent →
Modules
Skills and tools that give it its powers.
What the agent can do and what it can reach. Capability packs are open and horizontal. Industry modules bundle the packs, skills, and regulatory knowledge one sector needs.
- Seeded
- 35+ skills, 50+ tools, five packs, six industry modules.
- Tuned
- Your own skills and tools: the functions, data, and workflows only your company has.
/modules →
// Context → Agent → Powers · every layer: a head start, then yours
// Why AgentLayer
The model is not the moat. The context around it is.
Frontier models are interchangeable and get better every quarter. Buying seats to one does not make a business AI-native. What makes an agent useful inside a company is what it knows before it starts, what it is allowed to do, and what gets recorded when it acts.
That knowledge compounds. An agent that has read six months of your decisions, corrections, and sessions answers differently from one reading a bare repo, and no amount of money skips to month six. The context is the asset. The harness is what makes it safe to use.
AgentLayer builds both, open and self-hosted, and tunes them to your company one layer at a time.
// The Agentic Shift
// Open foundation · private recipe
The head start is the same for everyone. What compounds on top is yours.
Everything we ship is open source and self-hosted. Everything we tune is your company’s own and never leaves your infrastructure. Forward-deployed engineers do the tuning, layer by layer.
01 · Context
Platform
Ships
The brain architecture, the capture and compile pipeline, a seed bundle from eleven prompts.
Tuned
Your corpus seeded in, your capture sources wired, your manual and rules written for how you actually work.
02 · Harness
Agent
Ships
The open-source agent, host-neutral, running in production daily.
Tuned
Forked under your keys, named, given a character, permission rails set to your data classification, wired into your workflow.
03 · Powers
Modules
Ships
35+ skills, 50+ tools, five packs, six industry modules.
Tuned
Your own skills and tools: the functions, data, and workflows only your company has.
// Layer 03 · Modules · Powers
Modules are the agent’s powers: the skills it runs and the tools it reaches. Capabilities ship open and switch on when you add a credential. Industry modules bundle the capabilities, skills, and regulatory knowledge one sector needs.
// Capabilities · a selection
35+ skills · 50+ tools · see every capability →Plan and run · the work
Projects and tasks
One markdown file per task with frontmatter and a thread. A board that regenerates from them.
create-project
Roadmap
A north-star plan rendered as one self-contained HTML page: lanes, milestones, horizons.
roadmap
Goals ladder
Yearly, monthly, and weekly goals set by interview and tied to real tasks.
yearly-goals
Build and ship · the code
Worktrees
Parallel agents on one repo: sibling worktrees created, bootstrapped with your local config, and torn down.
setup-worktree
Pull-request review
Adversarial review of a teammate’s PR with paste-ready comments at file and line; reply mode for your own. A deploy health check verifies the rollout.
pr-review
API collections
Requests drafted as Bruno collections, or plain curl, that you fire from your own client.
api-collections
Reach and see · the world
Browser
A bundled headless browser for screenshots, styled PDFs, page-to-Markdown, and recordings, plus scripted flows that sign in and click through real pages.
browser-flows
Logs and uptime
Your telemetry, queried from the session: a request timeline by correlation ID, error rates, incidents, and the log lines behind a customer report.
betterstack
Database, read-only
Queries and schema against a production replica, or a fork you can break.
database_query
Brain and memory · the context
Capture
Feed the brain anything: a thought, a file, a URL, the clipboard, a correction.
capture
Compile
Raw sessions and captures become a structured wiki that loads next session.
knowledge-compile
Self-review
Accumulated feedback, read together, turned into changes to the agent’s own prompts.
self-review
// Industry modules
AgentPay
Payments & Financial Operations
AgentLayer Platform deployed for payments, financial operations, and the new agent-as-customer demographic.
/modules/finance →
AgentGov
Government & Public-Sector Workflows
AgentLayer Platform deployed for public-sector workflows, citizen services, and agency operations.
/modules/gov →
AgentEdu
Education Operations
AgentLayer Platform deployed for education operations: admissions, registrar, student services, multilingual support, faculty operations.
/modules/edu →
AgentHealth
Healthcare Operations
AgentLayer Platform deployed for healthcare operations. Clinician-augmenting, never clinician-replacing.
/modules/health →
AgentLegal
Legal Work
AgentLayer Platform deployed for legal work. Lawyer-augmenting, citation-disciplined, privileged-by-default.
/modules/legal →
AgentStay
Hospitality Operations
AgentLayer Platform deployed for hospitality. Operator-augmenting, multilingual, PMS-native, halal-aware.
/modules/stay →
// The dashboard · one HTML file
One page. The whole company.
Every home renders a mission-control page as a single static file. No server, no accounts, nothing to deploy. It is where operators live, and the fastest way to watch the brain work.
A real render · demo data · a fictitious company
// The pages
- Today
- the plan, what is in flight, what is waiting on someone
- Tasks
- every project on one board, by due horizon, never stale
- Projects
- progress and last touch, per project, with its roadmap
- Sessions
- what the agents worked on, captured automatically
- Brain
- the compiled knowledge and what loads each session
- Reports
- briefings, audits, and reviews, dated and clickable
35+
skills, one slash command each
50+
tools the agent can reach
2
hosts: Claude Code and Codex
Open source
Apache-2.0: fork it, keep it, no lock-in
// Proof Before Promises
// Malaysia-Built · Region-Ready
AgentLayer is built in Malaysia with ASEAN-native context. We are aligned with the Malaysia Digital (MDEC) program and the country's AI Nation ambitions, bringing regional understanding to enterprise-grade agent infrastructure.
// Principles
Product-first over services-first.
We ship software, not slide decks. Repeatable products that compound across customers, not bespoke engagements that don’t.
Human oversight in high-stakes domains.
Finance, healthcare, legal, government. Approval points and audit trails are designed in. Humans stay in command of consequential decisions.
Privacy and sovereignty by design.
Data residency, regional compliance, and tenant isolation are foundational, not features added under regulator pressure later.
Regional credibility, global standards.
Built in Malaysia for Southeast Asia’s regulatory reality, engineered to the standards expected anywhere agents touch real money or real people.
Become AI-native.
Forward-deployed engineering, custom-tuned per industry. Pre-revenue customers and design partnerships welcomed in select industries.
How AgentLayer engages →