Set up skill memory for your agent in 3 steps
Create a learning space and run a session
import os
from acontext import AcontextClient
client = AcontextClient(api_key=os.getenv("ACONTEXT_API_KEY"))
# Create a learning space
space = client.learning_spaces.create()
# Create a session and associate it with the space
session = client.sessions.create()
client.learning_spaces.learn(space.id, session_id=session.id)
# Run your agent as usual — store messages along the way
client.sessions.store_message(session.id, blob={"role": "user", "content": "My name is Gus"})
# ... agent runs and completes the task ...
.learn() before the agent runs. When tasks complete during the session, Acontext automatically picks them up for learning.Learning happens automatically
sessions = client.learning_spaces.list_sessions(space.id)
for s in sessions:
print(f"Session {s.session_id}: {s.status}")
# pending → running → completed
Inspect the learned skills
skills = client.learning_spaces.list_skills(space.id)
for skill in skills:
print(f"\n=== {skill.name} ===")
print(f"Description: {skill.description}")
print(f"Files:")
for f in skill.file_index:
print(f" {f.path}")
content = client.skills.get_file(skill_id=skill.id, file_path=f.path)
print(content.content.raw)