Skill Memory for
Claude Code
With Acontext, your agents can improve themselves via dynamic skill.
Captures what works, distills it into skills, and sync them to local.
How Acontext Connects
Your agent runs, Acontext captures the session, distills skills, and feeds them back — a continuous learning loop.
How Skill Memory Works
Learn from runs. Write as Markdown. Reuse anywhere. Skill memory that turns what your agents did into files they can read and use again.
I'm Gus, backend lead at MemoDB. Gener handles infra.
Got it — saved your role and team context.
Staging deploy failed — pods crashing with OOM
Found it: memory limit was 256Mi, bumped to 512Mi. Redeployed OK.
I sent wrong params to /billing/charge — got 422
Fixed: amount was string, needs int. Also added validation rules.
I accidentally ran the migration on prod instead of staging
Rolled back in 3.2s. No data loss — schema restored.
CI is failing — wrong test command in the workflow
Fixed: was `npm test`, should be `go test ./...`. Pipeline green.
We use Go 1.22 and prefer table-driven tests
Noted — saved to your tech stack preferences.
Select a file to preview
Create a learning space, attach a session, and Acontext builds skill files from successful runs.
List and read learned skills as Markdown — use them in your agent with get_skill / get_skill_file.
from acontext import AcontextClient
client = AcontextClient(api_key="sk-ac-...")
# Create a learning space and attach a session
space = client.learning_spaces.create()
session = client.sessions.create()
client.learning_spaces.learn(space.id, session_id=session.id)
# Run your agent, store messages — when tasks complete, learning runs automatically
client.sessions.store_message(session.id, blob={"role": "user", "content": "My name is Gus"})
client.sessions.store_message(session.id, blob={"role": "assistant", "content": "Hi Gus! How can I help you today?"})
# ... agent runs ...
# List learned skills (Markdown files)
client.learning_spaces.wait_for_learning(space.id, session_id=session.id)
skills = client.learning_spaces.list_skills(space.id)
# Download all skill files to a local directory
for skill in skills:
client.skills.download(skill_id=skill.id, path=f"./skills/{skill.name}")Create a learning space, attach a session, and Acontext builds skill files from successful runs.
DocsSupporting Skill Memory
What we offer: skill memory — and the SDKs to use it.
Skill Memory
Learns from task outcomes → writes Markdown files (SKILL.md schema) → agent recalls via get_skill / get_skill_file. Human-readable, portable, no embeddings. Export as ZIP, use in any framework.
SDKs & Integrations
Ready to use with OpenAI, Anthropic, LangGraph, Agno, and other popular agent frameworks.
All of this exists to feed one thing: a skill memory layer you can read, edit, and move.
Self-Host in Seconds
Run the full Acontext stack on your own infrastructure with a single command.
curl -fsSL https://install.acontext.io | shCopied!