https://github.com/memodb-io/acontext
Data platform for context engineering. Context data platform that stores, observes and learns. Join the community❤️: https://discord.acontext.io
https://github.com/memodb-io/acontext
agent agent-development-kit agent-observability ai-agent anthropic context-data-platform context-engineering data-platform llm llm-observability llmops memory openai self-evolving self-learning
Last synced: 10 days ago
JSON representation
Data platform for context engineering. Context data platform that stores, observes and learns. Join the community❤️: https://discord.acontext.io
- Host: GitHub
- URL: https://github.com/memodb-io/acontext
- Owner: memodb-io
- License: apache-2.0
- Created: 2025-07-16T13:15:48.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2026-01-18T08:23:18.000Z (25 days ago)
- Last Synced: 2026-01-18T08:26:13.190Z (25 days ago)
- Topics: agent, agent-development-kit, agent-observability, ai-agent, anthropic, context-data-platform, context-engineering, data-platform, llm, llm-observability, llmops, memory, openai, self-evolving, self-learning
- Language: Go
- Homepage: https://acontext.io
- Size: 20.4 MB
- Stars: 2,671
- Watchers: 23
- Forks: 245
- Open Issues: 14
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Roadmap: ROADMAP.md
- Agents: AGENTS.md
Awesome Lists containing this project
- awesome-ChatGPT-repositories - Acontext - ⭐ 1.3k / One Place for Agents to Store, Observe, and Learn. Context Data Platform for Self-learning Agents, designed to simplify context engineering and improve agent reliability and task success rates. (NLP)
README
# 💡 Core Features
- **Context Storage**
- [Session](https://docs.acontext.io/store/messages/multi-provider): unified message storage for any llm, any modal.
- [Context Editing](https://docs.acontext.io/engineering/editing) - manage your context window in one api.
- [Disk](https://docs.acontext.io/store/disk): save/download artifacts with file path.
- [Agent Skills](https://docs.acontext.io/store/skill) - empower your agents with agent skills.
- [Sandbox](https://docs.acontext.io/store/sandbox) - run code, analyze data, export artifacts.
- **Context Observability**
- [Session Summary](https://docs.acontext.io/observe/agent_tasks): asynchronously summarize agent's progress and user feedback.
- [State Tracking](https://docs.acontext.io/observe/agent_tasks): collect agent's working status in near real-time.
- **View everything in one [dashboard](https://docs.acontext.io/observe/dashboard)**
Dashboard of Agent Success Rate and Other Metrics
# 🚀 Connect to Acontext
1. Go to [Acontext.io](https://acontext.io), claim your free credits.
2. Go through a one-click onboarding to get your API Key: `sk-ac-xxx`
💻 Self-host Acontext
We have an `acontext-cli` to help you do quick proof-of-concept. Download it first in your terminal:
```bash
curl -fsSL https://install.acontext.io | sh
```
You should have [docker](https://www.docker.com/get-started/) installed and an OpenAI API Key to start an Acontext backend on your computer:
```bash
mkdir acontext_server && cd acontext_server
acontext server up
```
> Make sure your LLM has the ability to [call tools](https://platform.openai.com/docs/guides/function-calling). By default, Acontext will use `gpt-4.1`.
`acontext server 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/
## Step-by-step Quickstart
We're maintaining Python [](https://pypi.org/project/acontext/) and Typescript [](https://www.npmjs.com/package/@acontext/acontext) SDKs. The snippets below are using Python.
> Click the doc link to see TS SDK Quickstart.
## Install SDKs
```bash
pip install acontext
```
### Initialize Client
```python
import os
from acontext import AcontextClient
# For cloud:
client = AcontextClient(
api_key=os.getenv("ACONTEXT_API_KEY"),
)
# For self-hosted:
client = AcontextClient(
base_url="http://localhost:8029/api/v1",
api_key="sk-ac-your-root-api-bearer-token",
)
```
### Store & Get Messages
> [Docs](https://docs.acontext.io/store/messages/multi-provider)
Store messages in OpenAI, Anthropic, or Gemini format. Auto-converts on retrieval.
```python
# Create session and store messages
session = client.sessions.create()
# Store text, image, file, etc.
client.sessions.store_message(
session_id=session.id,
blob={"role": "user", "content": "Hello!"},
format="openai"
)
# Retrieve in any format (auto-converts)
result = client.sessions.get_messages(session_id=session.id, format="anthropic")
```
### Context Engineering
> [Session Summary](https://docs.acontext.io/engineering/session_summary) | [Context Editing](https://docs.acontext.io/engineering/editing)
Compress context with summaries and edit strategies. Original messages unchanged.
```python
# Session summary for prompt injection
summary = client.sessions.get_session_summary(session_id)
system_prompt = f"Previous tasks:\n{summary}\n\nContinue helping."
# Context editing - limit tokens on retrieval
result = client.sessions.get_messages(
session_id=session_id,
edit_strategies=[
{"type": "remove_tool_result", "params": {"keep_recent_n_tool_results": 3}},
{"type": "token_limit", "params": {"limit_tokens": 30000}}
]
)
```
### Agent Storage Tools
Disk Tool
> [Tool Docs](https://docs.acontext.io/tool/disk_tools) | [SDK Docs](https://docs.acontext.io/store/disk)
>
Persistent file storage for agents. Supports read, write, grep, glob.
```python
from acontext.agent.disk import DISK_TOOLS
from openai import OpenAI
disk = client.disks.create()
ctx = DISK_TOOLS.format_context(client, disk.id)
# Pass to LLM
response = OpenAI().chat.completions.create(
model="gpt-4.1",
messages=[
{"role": "system", "content": f"You have disk access.\n\n{ctx.get_context_prompt()}"},
{"role": "user", "content": "Create a todo.md with 3 tasks"}
],
tools=DISK_TOOLS.to_openai_tool_schema()
)
# Execute tool calls
for tc in response.choices[0].message.tool_calls:
result = DISK_TOOLS.execute_tool(ctx, tc.function.name, json.loads(tc.function.arguments))
```
Sandbox Tool
> [Tool Docs](https://docs.acontext.io/tool/bash_tools) | [SDK Docs](https://docs.acontext.io/store/sandbox)
>
> Isolated code execution environment with bash, Python, and common tools.
```python
from acontext.agent.sandbox import SANDBOX_TOOLS
from openai import OpenAI
sandbox = client.sandboxes.create()
disk = client.disks.create()
ctx = SANDBOX_TOOLS.format_context(client, sandbox.sandbox_id, disk.id)
# Pass to LLM
response = OpenAI().chat.completions.create(
model="gpt-4.1",
messages=[
{"role": "system", "content": f"You have sandbox access.\n\n{ctx.get_context_prompt()}"},
{"role": "user", "content": "Run a Python hello world script"}
],
tools=SANDBOX_TOOLS.to_openai_tool_schema()
)
# Execute tool calls
for tc in response.choices[0].message.tool_calls:
result = SANDBOX_TOOLS.execute_tool(ctx, tc.function.name, json.loads(tc.function.arguments))
```
Sandbox with Skills
> [Tool Docs](https://docs.acontext.io/tool/bash_tools#mounting-skills-in-sandbox) | [SDK Docs](https://docs.acontext.io/store/skill)
>
> Mount reusable Agent Skills into sandbox at `/skills/{name}/`. [Download xlsx skill](https://github.com/memodb-io/Acontext-Examples/raw/refs/heads/main/python/interactive-agent-skill/xlsx.zip).
```python
from acontext import FileUpload
# Upload a skill ZIP (e.g., web-artifacts-builder.zip)
with open("web-artifacts-builder.zip", "rb") as f:
skill = client.skills.create(file=FileUpload(filename="web-artifacts-builder.zip", content=f.read()))
# Mount into sandbox
ctx = SANDBOX_TOOLS.format_context(
client, sandbox.sandbox_id, disk.id,
mount_skills=[skill.id] # Available at /skills/{skill.name}/
)
# Context prompt includes skill instructions
response = OpenAI().chat.completions.create(
model="gpt-4.1",
messages=[
{"role": "system", "content": f"You have sandbox access.\n\n{ctx.get_context_prompt()}"},
{"role": "user", "content": "Create an Excel file with a simple budget spreadsheet"}
],
tools=SANDBOX_TOOLS.to_openai_tool_schema()
)
# Execute tool calls
for tc in response.choices[0].message.tool_calls:
result = SANDBOX_TOOLS.execute_tool(ctx, tc.function.name, json.loads(tc.function.arguments))
```
You can download a full skill interactive demo with `acontext-cli`:
```shell
acontext create my-skill --template-path "python/interactive-agent-skill"
```
# 🧐 Use Acontext to build Agent
Download end-to-end scripts with `acontext`:
**Python**
```bash
acontext create my-proj --template-path "python/openai-basic"
```
More examples on Python:
- `python/openai-agent-basic`: openai agent sdk template
- `python/agno-basic`: agno framework template
- `python/openai-agent-artifacts`: agent can edit and download artifacts.
**Typescript**
```bash
acontext create my-proj --template-path "typescript/openai-basic"
```
More examples on Typescript:
- `typescript/vercel-ai-basic`: agent in @vercel/ai-sdk
> [!NOTE]
>
> Check our example repo for more templates: [Acontext-Examples](https://github.com/memodb-io/Acontext-Examples).
>
> We're cooking more full-stack Agent Applications! [Tell us what you want!](https://discord.acontext.io)
# 🔍 Document
To understand what Acontext can do better, please view [our docs](https://docs.acontext.io/)
# ❤️ Stay Updated
Star Acontext on Github to support and receive instant notifications
# 🏗️ Architecture
click to open
```mermaid
graph TB
subgraph "Client Layer"
PY["pip install acontext"]
TS["npm i @acontext/acontext"]
end
subgraph "Acontext Backend"
subgraph " "
API["API
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
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
```
# 🤝 Stay Together
Join the community for support and discussions:
- [Discuss with Builders on Acontext Discord](https://discord.acontext.io) 👻
- [Follow Acontext on X](https://x.com/acontext_io) 𝕏
# 🌟 Contributing
- Check our [roadmap.md](./ROADMAP.md) first.
- Read [contributing.md](./CONTRIBUTING.md)
# 🥇 Badges
 
```md
[](https://acontext.io)
[](https://acontext.io)
```
# 📑 LICENSE
This project is currently licensed under [Apache License 2.0](LICENSE).
