AI MEMORY FOR AGENTS · AGNO
Give your Agno agents knowledge they can use again.
We keep useful project knowledge available beyond a single run. Save a decision worth keeping, find it again and read the evidence behind it through Agno’s native memory tools.
Explicit save and recall through your local Claude-Mem worker.

KNOWLEDGE THAT LASTS
Your next run can start with what you learned.
Keep the decision beyond the run.
We store the project notes you choose to save, so the next workflow can build on what you already learned.
Connect your existing tools.
Our example uses Agno’s native MCPTools with project-binding tool hooks and your existing Claude-Mem worker. Keep your memory close to the tools your agent uses.
Go back to the evidence.
Search the project, inspect its timeline and retrieve the original record. The example checks the ID confirmed by the save receipt.
ILLUSTRATIVE NOTE · REAL TOOL SEQUENCE
A decision today. A reference for the next run.
“Run the smoke suite before releasing the application.”
An illustrative release decision using the actual example’s tool sequence. Choose the note, save it, keep its receipt and read it back before relying on it.
- 01
Choose the knowledge
Choose a project and the decision worth keeping. The demo saves a harmless release checklist.
- 02
Save and keep the receipt
Our worker confirms an observation ID. Identical example inputs reuse the existing fingerprint.
- 03
Find the context
Search the selected project and inspect the saved observation’s timeline.
- 04
Read the original
Retrieve the receipt’s exact record, even when newer notes move it out of the first search results.
START WITH ONE PROJECT
Connect. Save one decision. Read it back.
- Install Claude-Mem and start its worker. Follow the installation guide, then check
npx claude-mem doctor. Keep your existing worker settings. - Use the example from a source checkout. You need Node.js on PATH, Python 3.11 or later and the installed MCP bundle. If using a source-built bundle, run
npm run buildfirst. - Set your path and project. Replace the MCP script and working-directory paths and choose your project. Match custom
CLAUDE_MEM_DATA_DIRandCLAUDE_MEM_WORKER_PORTvalues to the running worker.
python3 -m venv .venv-agno
.venv-agno/bin/python -m pip install -r examples/agno/requirements.txt
export CLAUDE_MEM_MCP_SERVER="/absolute/path/to/claude-mem/plugin/scripts/mcp-server.cjs"
.venv-agno/bin/python examples/agno/memory.py --project "my-application" --cwd "/absolute/path/to/my-application"Check the result. The command returns your project, an observation_id, recalled: true and model_requests: 0. Repeat the same command: the observation ID should remain the same.
Use the example’s memory_tools context in your agent and pass list(memory.functions.values()) to Agno. Keep the context open while your model runs: these functions carry the project-binding hooks. Follow the full guide’s agent example with your chosen provider.
AI memory in production
70 days of work. One searchable memory.
Alessandro used our open-source engine across three machines for 70 days. His customized deployment captured the decisions, fixes and discoveries behind the work—and published the data.
- Observations captured
- 22,718
- Bug fixes recorded
- 1,262
- Decisions recorded
- 757
See how he made that knowledge searchable. Then give your own agents a memory to build on.

Before you connect
Does this capture every conversation automatically?
This example saves the notes your workflow explicitly supplies. It does not install capture hooks or inject startup context. Call the memory tools when your workflow needs them.
Do I need Pro or a model API key?
Neither is required for this local demonstration. The command exercises memory tools without a model request. Your own model-driven application needs its chosen provider and credentials.
Can I connect a hosted worker?
This example connects to your running local worker over the installed stdio MCP bundle. It does not configure hosted authentication or a cloud-runtime connection. Your worker’s existing sync settings still apply.
How do I keep projects separate?
The example’s tool hooks bind each read and write to the project you supply. Those filters are not account authorization; use separate authorized worker data directories across trust boundaries.
What if a save times out or the worker stops?
The example reports failure and queues no automatic retry. Check the worker and repeat the exact same project, title and text to recover its existing receipt when a write may have completed. Worker auto-start is disabled.
Which version should I install?
Use the checked-in requirements: Agno 3.1.12, FastMCP 4.1.8 and MCP 2.3.0. The source guide documents Python 3.12 on Linux and requires Python 3.11 or later. Windows and macOS acceptance are not established by this example.
How do I disconnect?
Close the memory-tools context and remove the example environment if no longer needed. It adds no capture hook or user MCP configuration. Existing memories remain in your worker.
Build on a working example.
Source reviewed November 20, 2026. The published fixture checks explicit save/recall, repeated-save identity, selected-project reads and offline failure with harmless notes. Its model-free verification is separate from a model-driven agent run.
Give your next agent run a useful starting point.
Keep the decision. Find its source. Build from there.