Acontext is a context data platform for building cloud-native AI Agents. It can:
- Store contexts & artifacts.
- Do context engineering for you.
- Observe agent tasks and user feedback.
- Enable agent self-learning by distilling skills from agent's completed tasks.
- View everything in one Dashboard.
Store, Observe and Learn
We're building it because we believe Acontext can help you:
- Build a more scalable agent product with better context engineering
- Improve your agent success rate and reduce running steps
so that your agent can be more stable and provide greater value to your users.
- Session - You can store context in Acontext, just like a Database but only used for context.
- Task Agent - Background TODO agent that collects task's status, progress and preferences.
- Disk - File storage for agent artifacts.
- Space - A Notion-like
Spacefor agents, where learned skills are stored.- Experience Agent - Background agents that distill, save and search skills.
┌──────┐ ┌────────────┐ ┌──────────────┐ ┌───────────────┐ │ User │◄──►│ Your Agent │◄──►│ Session │ │ Artifact Disk │ └──────┘ └─────▲──────┘ └──────┬───────┘ └───────────────┘ │ │ │ ┌────────▼────────┐ │ │ Observed Tasks │ │ └────────┬────────┘ │ │ │ ┌────────▼────────┐ │ │ Learn Skills │ # or wait for user confirmation │ └────────┬────────┘ │ │ └──────────────────┘ Skills guide the agent📖 Task Structure
{"task_description": "Star https://github.com/memodb-io/Acontext", "progresses": [ "I have navigated to Acontext repo", "Tried to Star but a pop-up required me to login", ... ], "user_preferences": [ "user wants to use outlook email to login" ] }📖 Skill Structure
{"use_when": "star a repo on github.com", "preferences": "use user's outlook account", "tool_sops": [{"tool_name": "goto", "action": "goto github.com"},{"tool_name": "click", "action": "find login button if any. login first"}, ... ] }📖 Space Structure
/ └── github/ (folder) └── GTM (page) ├── find_trending_repos (sop) └── find_contributor_emails (sop) └── basic_ops (page) ├── create_repo (sop) └── delete_repo (sop) ...Click to open the architecture diagram, if you're interested.
graph TB subgraph "Client Layer" PY["pip install acontext"] TS["npm i @acontext/acontext"] end subgraph "Acontext Backend" subgraph " " API["API<br/>localhost:8029"] CORE["Core"] API -->|FastAPI & MQ| CORE end subgraph " " Infrastructure["Infrastructures"] PG["PostgreSQL"] S3["S3"] REDIS["Redis"] MQ["RabbitMQ"] end end subgraph "Dashboard" UI["Web Dashboard<br/>localhost:3000"] end PY -->|RESTFUL API| API TS -->|RESTFUL API| API UI -->|RESTFUL API| API API --> Infrastructure CORE --> Infrastructure Infrastructure --> PG Infrastructure --> S3 Infrastructure --> REDIS Infrastructure --> MQ style PY fill:#3776ab,stroke:#fff,stroke-width:2px,color:#fff style TS fill:#3178c6,stroke:#fff,stroke-width:2px,color:#fff style API fill:#00add8,stroke:#fff,stroke-width:2px,color:#fff style CORE fill:#ffd43b,stroke:#333,stroke-width:2px,color:#333 style UI fill:#000,stroke:#fff,stroke-width:2px,color:#fff style PG fill:#336791,stroke:#fff,stroke-width:2px,color:#fff style S3 fill:#ff9900,stroke:#fff,stroke-width:2px,color:#fff style REDIS fill:#dc382d,stroke:#fff,stroke-width:2px,color:#fff style MQ fill:#ff6600,stroke:#fff,stroke-width:2px,color:#fff We have an acontext-cli to help you do quick proof-of-concept. Download it first in your terminal:
curl -fsSL https://install.acontext.io | shYou should have docker installed and an OpenAI API Key to start an Acontext backend on your computer:
mkdir acontext_server &&cd acontext_server acontext docker up📖 local setup Acontext requires at least an OpenAI API key. We recommend
gpt-5.1orgpt-4.1as the LLM model
acontext docker up will create/use .env and config.yaml for Acontext, and create a db folder to persist data.
Once it's done, you can access the following endpoints:
- Acontext API Base URL: http://localhost:8029/api/v1
- Acontext Dashboard: http://localhost:3000/
Dashboard of Agent Success Rate and Other Metrics
Download end-to-end scripts with acontext:
Python
acontext create my-proj --template-path "python/openai-basic"More examples on Python:
python/openai-agent-basic: self-learning agent in openai agent sdk.python/agno-basic: self-learning agent in agno frameworkd.python/openai-agent-artifacts: agent that can edit and download artifacts.
Typescript
acontext create my-proj --template-path "typescript/openai-basic"More examples on Typescript:
typescript/vercel-ai-basic: self-learning agent in @vercel/ai-sdk
Check our example repo for more templates: Acontext-Examples.
Click to Open
We're maintaining Python 
pip install acontext # for Python npm i @acontext/acontext # for Typescript fromacontextimportAcontextClientclient=AcontextClient( base_url="http://localhost:8029/api/v1", api_key="sk-ac-your-root-api-bearer-token" ) client.ping() # yes, the default api_key is sk-ac-your-root-api-bearer-tokenAcontext can manage agent sessions and artifacts.
Save Messages 📖
Acontext offers persistent storage for message data. When you call session.send_message, Acontext will persist the message and start to monitor this session:
Code Snippet
session=client.sessions.create() messages= [{"role": "user", "content": "I need to write a landing page of iPhone 15 pro max"},{"role": "assistant", "content": "Sure, my plan is below:\n1. Search for the latest news about iPhone 15 pro max\n2. Init Next.js project for the landing page\n3. Deploy the landing page to the website", } ] # Save messagesformsginmessages: client.sessions.send_message(session_id=session.id, blob=msg, format="openai")📖 We also support multi-modal message storage and anthropic SDK.
Load Messages 📖
Obtain your session messages using sessions.get_messages
Code Snippet
r=client.sessions.get_messages(session.id) new_msg=r.itemsnew_msg.append({"role": "user", "content": "How are you doing?"}) r=openai_client.chat.completions.create(model="gpt-4.1", messages=new_msg) print(r.choices[0].message.content) client.sessions.send_message(session_id=session.id, blob=r.choices[0].message)
You can view sessions in your local Dashboard
Artifacts 📖
Create a disk for your agent to store and read artifacts using file paths:
Code Snippet
fromacontextimportFileUploaddisk=client.disks.create() file=FileUpload( filename="todo.md", content=b"# Sprint Plan\n\n## Goals\n- Complete user authentication\n- Fix critical bugs" ) artifact=client.disks.artifacts.upsert( disk.id, file=file, file_path="/todo/" ) print(client.disks.artifacts.list( disk.id, path="/todo/" )) result=client.disks.artifacts.get( disk.id, file_path="/todo/", filename="todo.md", with_public_url=True, with_content=True ) print(f"✓ File content: {result.content.raw}") print(f"✓ Download URL: {result.public_url}") 
You can view artifacts in your local Dashboard
Observe 📖
For every session, Acontext will automatically launch a background agent to track the task progress and user feedback. It's like a background TODO agent. Acontext will use it to observe your daily agent success rate.
You can use the SDK to retrieve the current state of the agent session, for Context Engineering like Reduction and Compression.
Full Script
fromacontextimportAcontextClient# Initialize clientclient=AcontextClient( base_url="http://localhost:8029/api/v1", api_key="sk-ac-your-root-api-bearer-token" ) # Create a project and sessionsession=client.sessions.create() # Conversation messagesmessages= [{"role": "user", "content": "I need to write a landing page of iPhone 15 pro max"},{"role": "assistant", "content": "Sure, my plan is below:\n1. Search for the latest news about iPhone 15 pro max\n2. Init Next.js project for the landing page\n3. Deploy the landing page to the website", },{"role": "user", "content": "That sounds good. Let's first collect the message and report to me before any landing page coding.", },{"role": "assistant", "content": "Sure, I will first collect the message then report to you before any landing page coding.", "tool_calls": [{"id": "call_001", "type": "function", "function":{"name": "search_news", "arguments": "{\"query\": \"iPhone news\"}" } } ] }, ] # Send messages in a loopformsginmessages: client.sessions.send_message(session_id=session.id, blob=msg, format="openai") # Wait for task extraction to completeclient.sessions.flush(session.id) # Display extracted taskstasks_response=client.sessions.get_tasks(session.id) print(tasks_response) fortaskintasks_response.items: print(f"\nTask #{task.order}:") print(f" ID: {task.id}") print(f" Title: {task.data['task_description']}") print(f" Status: {task.status}") # Show progress updates if availableif"progresses"intask.data: print(f" Progress updates: {len(task.data['progresses'])}") forprogressintask.data["progresses"]: print(f" - {progress}") # Show user preferences if availableif"user_preferences"intask.data: print(" User preferences:") forprefintask.data["user_preferences"]: print(f" - {pref}")
flushis a blocking call, it will wait for the task extraction to complete. You don't need to call it in production, Acontext has a buffer mechanism to ensure the task extraction is completed right on time.
Example Task Return:
Task #1: Title: Search for the latest news about iPhone 15 Pro Max and report findings to the user before any landing page coding. Status: success Progress updates: 2 - I confirmed that the first step will be reporting before moving on to landing page development. - I have already collected all the iPhone 15 pro max info and reported to the user, waiting for approval for next step. User preferences: - user expects a report on latest news about iPhone 15 pro max before any coding work on the landing page. Task #2: Title: Initialize a Next.js project for the iPhone 15 Pro Max landing page. Status: pending Task #3: Title: Deploy the completed landing page to the website. Status: pendingYou can view the session tasks' statuses in the Dashboard:
A Task Demo
Acontext can gather a bunch of sessions and learn skills (SOPs) on how to call tools for certain tasks.
Learn Skills to a Space📖
A Space can store skills, and memories in a Notion-like system. You first need to connect a session to Space to enable the learning process:
# Step 1: Create a Space for skill learningspace=client.spaces.create() print(f"Created Space: {space.id}") # Step 2: Create a session attached to the spacesession=client.sessions.create(space_id=space.id) # ... push the agent working contextThe learning happens in the background and is not real-time (delay around 10-30s).
What Acontext will do in the background:
graph LR A[Task Completed] --> B[Task Extraction] B --> C{Space Connected?} C -->|Yes| D[Queue for Learning] C -->|No| E[Skip Learning] D --> F[Extract SOP] F --> G{Hard Enough?} G -->|No - Too Simple| H[Skip Learning] G -->|Yes - Complex| I[Store as Skill Block] I --> J[Available for Future Sessions] Eventually, SOP blocks with tool-call pattern will be saved to Space. You can view every Space in the Dashboard:
A Space Demo
Search Skills from a Space📖
To search skills from a Space and use them in the next session:
result=client.spaces.experience_search( space_id=space.id, query="I need to implement authentication", mode="fast" )Acontext supports fast and agentic modes for search. The former uses embeddings to match skills. The latter uses an Experience Agent to explore the entire Space and tries to cover every skill needed.
The return is a list of sop blocks, which look like below:
{"use_when": "star a github repo", "preferences": "use personal account. star but not fork", "tool_sops": [{"tool_name": "goto", "action": "goto the user given github repo url"},{"tool_name": "click", "action": "find login button if any, and start to login first"}, ... ] }To understand what Acontext can do better, please view our docs
Star Acontext on Github to support and receive instant notifications
Join the community for support and discussions:
- Check our roadmap.md first.
- Read contributing.md
This project is currently licensed under Apache License 2.0.
[](https://acontext.io)[](https://acontext.io)
