PERSISTENT AGENT API

■ THE MEMORY LAYER FOR SERVER-SIDE AGENTS.

TURN YOUR API
INTO AN AGENT
THAT REMEMBERS.

Define the agent once on your server: its profile, system prompt, instructions, history and approved lessons. Every API call starts with the context it needs—not another round of setup.

Create your agent ↗See how it works ↓

One agent ID. Your model provider. Your application runs the tools.

▪ ▪ ▪your-agent.profile01 / SAVED

> meet your new agent

✳

Support agent

Customer support agent

EXAMPLE
Instructions
Saved once
Memory
You choose
Model
Your connected provider
Learning
Approval required
// Every request can be this simple.
{
  "agent_id": "support_agent",
  "input": [{ "role": "user", "content": "Help my customer." }]
}
The same agent, ready for the next request.
01   AGENT PROFILE02   SYSTEM INSTRUCTIONS03   RELEVANT HISTORY04   APPROVED LESSONS

THE MODEL IS ONLY PART OF THE AGENT.

CONTEXT SHOULD NOT
BE REBUILT ON EVERY CALL.

A model can answer well, but it does not know your agent’s role, its decisions or the customer history behind a request. That context should live with the agent—not be reconstructed in every application call.

WITHOUT OSAGENTSREASSEMBLE CONTEXT

Your application rebuilds the agent.

  • Repeat the system prompt
  • Store and search conversation history
  • Decide what belongs in each request
  • Turn feedback into safe, versioned rules
WITH OSAGENTSONE AGENT API

Your agent arrives ready to work.

  • Keep its profile and instructions on the server
  • Retrieve relevant memory automatically
  • Bring forward history only when it helps
  • Review and approve what it learns

You keep control. Bring your model API key. Keep tools inside your application. osAgents manages the persistent agent context between them.

DEFINE ONCE. KEEP BUILDING.

YOUR AGENT IS READY
WHEN YOUR API CALLS.

Your app sends the task.
osAgents brings the context.

[ 01 / DEFINE ]
NAMESupport agentINSTRUCTIONS

Be helpful. Keep answers short.
Ask when information is missing.

↳ Saved to the agent profile

Tell it who it is.

Give your agent a name, a role and clear instructions. Edit them whenever you need.

[ 02 / CONNECT ]
MODEL CONNECTIONYour provider. Your key.
osAgents→Model API
↳ No model training needed

Connect your model.

Bring a supported model provider’s API key. osAgents adds the saved context before calling it.

[ 03 / BUILD ]
YOUR APPLICATIONSend a message.
agent_id: support_agent
input: “Let’s get started.”
↳ Receive the agent’s response

Use it in your app.

Call your agent through the API. Your application stays in charge of tools and actions.

Your application sends an agent ID and a message. osAgents resolves the agent context before the model call.

MEMORY, WITHOUT THE MYSTERY.

THE RIGHT MEMORY.
ONLY WHEN NEEDED.

Chat history, saved preferences and knowledge can live behind one agent ID. You choose what is kept, how long it stays and who it belongs to.

osAgents searches memory privately. The model receives only the relevant pieces—not your entire memory store—and memory never changes the model’s weights.

Chat historyPreferencesKnowledgeApproved lessons
Explore the memory preview ↗
01AUTOMATIC

Relevant context, before the model answers.

For every request, osAgents first narrows memory by workspace, agent, end user and session. It selects the most relevant recent chat turns, facts and approved lessons, then adds them to the model context.

Your message→Private retrieval→Model context
No tool call. No extra step in your application.
02ON DEMAND

A deeper recall, only when it needs one.

If the initial context is not enough, the agent can request recall_memory. osAgents performs another bounded, read-only search and returns the result privately so the model can finish its answer.

Needs more→Private recall→Continue answer
Still internal to osAgents. It is never returned as a customer tool.
One protected memory indexWorkspace → Agent → End user → SessionInspectable · deletable · retention controlled

LEARN FROM FEEDBACK. NOT GUESSWORK.

BETTER HABITS.
WITH YOUR APPROVAL.

Correct an answer. Review a suggested lesson.
Choose whether your agent should keep it.

01 / YOUR CORRECTION

“Please write dates
as YYYY-MM-DD.”

02 / PROPOSED LESSON

Use YYYY-MM-DD
for invoice dates.

AWAITING APPROVAL
03 / APPROVED VERSION

A saved rule for
future invoice requests.

v2 · reversible

Learning updates approved instructions and memory—not model weights. Changes can be tested and rolled back; improvement is not guaranteed.

A SMALL PREVIEW. A CLEAR IDEA.

MAKE IT YOURS.

Change the profile. See what your app sends.
No API key needed for this example.

01 / AGENT PROFILE INTERACTIVE EXAMPLE

Example only. Nothing is sent or saved to a server.

02 / YOUR API REQUESTAPI CONTRACT

You send the message, not the whole profile.

osAgents adds on the server
Profile
Support agent · Customer support
Instructions
From the saved profile
History
This session
ILLUSTRATIVE RESPONSE · NOT AI-GENERATED
“Happy to help. What does your customer need?”


request.sh
curl http://127.0.0.1:4331/v1/messages \
	  -H "Authorization: Bearer YOUR_OSAGENTS_KEY" \
	  -H "Idempotency-Key: UNIQUE_REQUEST_ID" \
	  -H "Content-Type: application/json" \
	  -d '{
	    "agent_id": "support_agent",
	    "session_id": "customer_1042",
	    "input": [{"role":"user","content":"Help with this order."}]
	  }'
Local reference endpoint. Replace the key before running.
BUILT FOR YOUR APPLICATION.
ONE REQUEST.
YOUR SAVED AGENT.
No system prompt to paste into every call. No conversation database to build from scratch.
Use an agent ID and, when memory is enabled, a session ID. Receive a response your application can use.
Your tools stay yours.
osAgents does not execute your tools. If your agent requests a tool call, your application decides whether to run it and sends back the result.


PAID FROM THE FIRST LIVE WORKSPACE.
START SMALL.
GROW WITH USE.
No hosted free tier and no seat plans. One monthly entry plan, then transparent usage.
The price-to-fully-loaded-cost ratio must remain at least 10× before this candidate rate card can go live.
LAUNCH PRICE CANDIDATECOST VALIDATION REQUIRED
$20 / month
per workspace
CANDIDATE
Agent runs
10,000 included
More runs
$3 / 1,000
Memory
1 GB included
More memory
$8 / GB-month
Model inference
Paid through your BYOK provider
Tool continuations and up to three private recalls stay inside the original run.


A FEW THINGS TO KNOW.
GOOD QUESTIONS.
CLEAR ANSWERS.
Do I need to train or fine-tune a model?
No. The initial product uses saved instructions and relevant memory with a connected model. That changes the context sent to the model, not its weights.
Can I bring my own model API key?
Yes. You connect a supported OpenAI-compatible provider; osAgents manages your agent’s profile and context. Provider inference charges remain separate.
What does the agent remember?
You choose whether to retain session history and save longer-term facts or preferences. Memories are inspectable and deletable, and separated by workspace, agent and end user.
Does “learning” mean it gets smarter automatically?
No. Feedback can produce suggested lessons. Approved, versioned lessons influence later responses. They do not train the underlying model, and they can be wrong—so evaluation and rollback matter.
Where does my data go?
The proposed service stores enabled profiles and memory on our servers. Instructions, messages and selected memory are sent to your connected model provider for inference. Final production regions and retention terms must be published before launch.
Does osAgents run tools or route between models?
Your application runs the tools. This product focuses on persistent agent profiles, memory and controlled learning—not a multi-model router or an orchestration platform.
Can I use this today? What does it cost?
This page is still a preview and collects no payment. The launch candidate is $20 per workspace each month, including 10,000 runs and 1 GB memory, then $3 per 1,000 runs and $8 per GB-month. It will not be published as a live Price until the 10× cost gate passes.


THE AGENT LAYER BETWEEN YOUR APP AND YOUR MODEL.
SET IT ONCE.
KEEP THE CONTEXT.
Configure your agent ↗