memorizz
MemoRizz: A Python library serving as a memory layer for AI applications. Leverages popular databases and storage solutions to optimize memory usage. Provides utility classes and methods for efficient data management.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/richmondalake/memorizz with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/richmondalake/memorizz'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/richmondalake--memorizz)HTML
<a href="/listings/richmondalake--memorizz"><img src="/api/listings/richmondalake--memorizz/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Requires Python 3.10+. Install and launch the CLI with a cloud model:
python -m pip install memorizz export OPENAI_API_KEY="your-key" memorizz
For a fully local setup, use [Ollama](docs/getting-started/cli.md#option-a-local-no-api-key-ollama). The [installation guide](docs/getting-started/installation.md) covers `uv`, `pipx`, npm, Homebrew, and optional integrations.
Save credentials without putting them in shell history, and choose memory storage independently from the model:
memorizz config set OPENAI_API_KEY # hidden prompt memorizz memory configure # guided memory-provider setup memorizz notion connect # Notion library + separate vector provider memorizz config path # actual save target and precedence
These commands save defaults for the next launch; they do not switch a running agent or migrate memory. See [CLI configuration](docs/getting-started/cli.md#configuration).
Build a memory-first agent in Python using the same environment:
from memorizz import MemAgentBuilder
agent = (
MemAgentBuilder()
.with_instruction("Remember useful context and use it to help the user.")
.with_llm_config({"provider": "openai", "model": "gpt-4o-mini"})
.with_memory_ids("my-assistant")
.build_and_save()
)
scope = {"memory_id": "my-assistant", "user_id": "alice", "thread_id": "intro"}
with agent.lifecycle(close_memory_provider=True):
agent.run("I work on payments systems.", **scope)
print(agent.run("What did I tell you about my work?", **scope))Memory persists under `~/.memorizz/memory` by default. Save `agent.agent_id` to [restore the agent later](docs/getting-started/python-sdk-quickstart.md#5-restore-it-later).
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 18 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- {
- "name": "memorizz",
- "owner": {
- "name": "Richmond Alake",
- "url": "https://github.com/RichmondAlake"
- },
- "metadata": {
- "description": "MemoRizz plugins: durable project memory for coding agents."
- },
- "plugins": [
- {
- "name": "memorizz",
- "source": "./plugins/claude-code/memorizz",
- "description": "Durable, searchable project memory for Claude Code, shared with Codex and your MemoRizz agents.",
- "category": "productivity"
- }
- ]
- }
README.md · README · 230 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # Memorizz
- **The intelligence plane for memory-first agents.**
- Memorizz is a Python framework that connects persistent memory, models, prompts,
- and reasoning so agents can recall what matters, reuse experience, and make
- better decisions across sessions.
- [Documentation](https://richmondalake.github.io/memorizz/) ·
- [PyPI](https://pypi.org/project/memorizz/) ·
- [Examples](examples/zero_to_hero/README.md) ·
- [Changelog](CHANGELOG.md)
- <picture>
- <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/RichmondAlake/memorizz/main/docs/assets/screenshots/dashboard-dark.png">
- <img alt="The MemoRizz agent dashboard: runs, success rate, run time, model calls, tokens and spend across every agent, a runs-over-time chart, and what needs attention." src="https://raw.githubusercontent.com/RichmondAlake/memorizz/main/docs/assets/screenshots/dashboard-light.png">
- </picture>
- *The agent dashboard in the local UI (`memorizz ui`): runs, success rate, run
- time, model calls, tokens and spend across every agent, and what needs
- attention.*
- ## Memory management
- Memory is the foundation: retain information, retrieve relevant context, and
- refine what an agent knows over time.
- | Memory | What it gives your agents |
- |---|---|
- | [Episodic](docs/memory-types/episodic.md) | Conversation history, past interactions, and summaries. |
- | [Semantic](docs/memory-types/semantic.md) | Knowledge bases, entity facts, preferences, and personas. |
- | [Procedural](docs/memory-types/procedural.md) | Registered tools, recorded workflows, and reusable skills. |
- | [Short-term](docs/memory-types/short-term.md) | Working context and semantic caching. |
- | [Shared](docs/memory-types/shared.md) | A shared workspace for agent coordination and handoffs. |
- - **Persist and isolate:** scope memory by agent, user, and conversation. Start
- with local filesystem storage, or use MongoDB, Oracle, or
- [Notion with separate vector storage](docs/memory-providers/notion.md) through the same
- provider contract.
- - **Ingest and retrieve:** turn files and folders into a knowledge base with
- configurable chunking, embeddings, and semantic or hybrid search.
- - **Manage context:** deduplicate retrieved memories, summarize and compact
- history, inspect recall decisions, and control retention and forgetting.
- - **Forget the way Generative Agents do:** retrieval ranks memories by recency
- since last use, stored importance and relevance, recalls reinforce a memory,
- and a governed planner suppresses, never deletes, records whose retention
- decayed; every suppression is approved and reversible. See the
- [forgetting mechanism](docs/guides/forgetting-mechanism.md).
- Explore [memory concepts and scope](docs/getting-started/concepts.md),
- [storage providers](docs/memory-providers/filesystem.md), and
- [context efficiency](docs/guides/context-efficiency.md).
- ## Agent framework
- Build persistent agents with `MemAgent` and `MemAgentBuilder`. Choose
- `assistant`, `workflow`, or `deep_research` modes and connect cloud or local
- [model providers](docs/getting-started/model-providers.md).
- - **Tools and integrations:** Python functions, MCP servers, internet search,
- governed browser control, [desktop control](docs/desktop-control/index.md)
- of Mac apps (computer use), sandboxes, and external skills. MCP tools are
- stored in toolbox memory and found by meaning. A
- [tool call cache](docs/guides/context-efficiency.md#tool-call-cache) reuses
- the results of repeated calls to tools that are safe to reuse.
- - **Persona:** give an agent a name, role, goals and background. It changes
- when someone asks, and with
- [persona learning](docs/guides/persona-learning.md) on, it can grow in the
- background from what the agent is used for, with every change quoted and
- undoable.
- - **Coordination:** delegate work to specialist agents, share memory, run
- scheduled automations, and start [timers](docs/guides/automations.md#timers)
- that count down live in the CLI and the chat.
- - **Interfaces:** use the Python SDK, interactive CLI, local web UI, or expose
- Memorizz as an MCP server.
- Start with the [SDK quickstart](docs/getting-started/python-sdk-quickstart.md)
- or the [CLI guide](docs/getting-started/cli.md).
- ## Harness
- `MetaHarness` runs tasks through Codex, Claude Code, OpenHands, DeepSeek, pi,
- Hermes, or native MemAgent workers, and a MemAgent can hand parts of a request
- to delegates that run on those harnesses. It carries memory scope and learning evidence across
- harnesses while managing permissions, approvals, workspace isolation, budgets,
- cancellation, and host-side verification.
- Use an external harness for an entire task or let a MemAgent call one as a
- specialist tool. Inspect installed adapters with `memorizz harness doctor`.
- See the [MetaHarness guide](docs/guides/meta-harness.md) and
- [hands-on examples](examples/metaharness/README.md).
- <picture>
- <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/RichmondAlake/memorizz/main/docs/assets/screenshots/harnesses-dark.png">
- <img alt="The MemoRizz harness dashboard: launch a task on a harness, see which harnesses are ready on this machine, and follow plans and comparisons across Codex, Claude Code and MemAgents." src="https://raw.githubusercontent.com/RichmondAlake/memorizz/main/docs/assets/screenshots/harnesses-light.png">
- </picture>
- *The harness dashboard: run a memory-grounded task on one harness, chain
- harnesses into a plan, or compare them side by side, with approvals and
- verification.*
- ### Memory for Codex and Claude Code
- MemoRizz is also a plugin for Codex and Claude Code. The agent starts each
- session with the project's facts and the last session's summary; each turn and
- a summary of each session are saved as episodic memory; and the agent can
- search past sessions, save and correct facts, record entities and load project
- documents. Both agents share the memory, locally or on a hosted MemoRizz MCP
- server for a team ([deploy/mcp-server](deploy/mcp-server/README.md)). Each
- session also appears on the UI's Harnesses page with its full trajectory, so
- you can follow a Codex session and a Claude Code session step by step and
- compare them.
- ```bash
- memorizz plugin install codex # or: memorizz plugin install claude-code
- ```
- Or `codex plugin marketplace add RichmondAlake/memorizz` /
- `claude plugin marketplace add RichmondAlake/memorizz`, then install
- `memorizz@memorizz`. See [MemoRizz in Codex and Claude Code](docs/guides/coding-agent-plugins.md),
- and [examples/coding_agent_plugins](examples/coding_agent_plugins/README.md) for
- Codex and Claude Code sharing one project's memory.
- ## Continual learning and the intelligence plane
- The **intelligence plane** is the model layer and everything that helps it
- think: the LLM, prompts, reasoning strategies such as planning, reflection, and
- tool selection, plus the memory and retrieval that supply context. Its job is
- **decision quality**. A bad plan or a hallucinated tool call is an intelligence
- plane problem.
- Memorizz makes memory the foundation of this plane. Its opt-in continual
- learning loop captures tool workflows and their outcomes, distills repeated
- successful procedures into reusable skills, retrieves relevant active skills,
- and monitors their performance. Shadow evaluation and review support skill
- activation; skills that stop working can be demoted.
- The learning control plane adds traceable outcome evidence, bounded retrieval,
- and reversible forgetting. Together, these capabilities help agents retain,
- recall, reuse, and refine experience.
- Memorizz also fine-tunes the small models behind memory on your own
- memories: decision models that file each memory in the right store,
- embedding models (EmbeddingGemma 2, Qwen3-Embedding) and rerankers. The
- datasets stay in the connected memory provider, each model is scored against
- the one in use on held-out examples, and you swap it in (or back) from the
- UI, the CLI or MCP.
- Where memory used to decide with a similarity score and a fixed threshold, an
- agent can ask a [decision model](docs/guides/decision-models.md) instead:
- Liquid's d1 on your machine, TypeSafe's Jev, OpenAI Decisions, or one
- fine-tuned in Memorizz. It answers whether a message holds anything worth
- keeping, which memory a request needs, whether a cached answer fits the
- question as asked, how a new note relates to stored ones, and which tool a
- request needs, if any.
- Read about [continual learning](docs/guides/continual-learning.md),
- [persona learning](docs/guides/persona-learning.md),
- [fine-tuning](docs/guides/fine-tuning.md),
- [decision models](docs/guides/decision-models.md), the
- [learning control plane](docs/guides/learning-control-plane.md), the
- [forgetting mechanism](docs/guides/forgetting-mechanism.md), and
- [evaluation methods](docs/evaluation-suite.md).
- ## Quick start
- Requires Python 3.10+. Install and launch the CLI with a cloud model:
- ```bash
- python -m pip install memorizz
- export OPENAI_API_KEY="your-key"
- memorizz
- ```
- For a fully local setup, use [Ollama](docs/getting-started/cli.md#option-a-local-no-api-key-ollama).
- The [installation guide](docs/getting-started/installation.md) covers `uv`,
- `pipx`, npm, Homebrew, and optional integrations.
- Save credentials without putting them in shell history, and choose memory
- storage independently from the model:
- ```bash
- memorizz config set OPENAI_API_KEY # hidden prompt
- memorizz memory configure # guided memory-provider setup
- memorizz notion connect # Notion library + separate vector provider
- memorizz config path # actual save target and precedence
- ```
- These commands save defaults for the next launch; they do not switch a running
- agent or migrate memory. See [CLI configuration](docs/getting-started/cli.md#configuration).
- Build a memory-first agent in Python using the same environment:
- ```python
- from memorizz import MemAgentBuilder
- agent = (
- MemAgentBuilder()
- .with_instruction("Remember useful context and use it to help the user.")
- .with_llm_config({"provider": "openai", "model": "gpt-4o-mini"})
- .with_memory_ids("my-assistant")
- .build_and_save()
- )
- scope = {"memory_id": "my-assistant", "user_id": "alice", "thread_id": "intro"}
- with agent.lifecycle(close_memory_provider=True):
- agent.run("I work on payments systems.", **scope)
- print(agent.run("What did I tell you about my work?", **scope))
- ```
- Memory persists under `~/.memorizz/memory` by default. Save `agent.agent_id` to
- [restore the agent later](docs/getting-started/python-sdk-quickstart.md#5-restore-it-later).
- ## Explore
- - [Memory-first tutorials](examples/zero_to_hero/README.md)
- - [Persistent notes and searchable history: filesystem and Oracle notebooks](examples/context_engineering/README.md)
- - [MCP connectivity](docs/guides/mcp-connectivity.md) and [MCP server](docs/guides/mcp-server.md)
- - [Automations and timers](docs/guides/automations.md) and [multi-user applications](docs/guides/multi-tenant.md)
- - [Observability](docs/observability-ui.md) and [evaluation suite](docs/evaluation-suite.md)
- - [Usage, cost and memory analytics](docs/usage-analytics.md)
- - [Persona learning](docs/guides/persona-learning.md) and [account-owned persona evolution](docs/persona-evolution-hosts.md)
- - [API reference](docs/reference/python-api.md), [configuration](docs/reference/configuration.md), and [troubleshooting](docs/troubleshooting.md)
- ## License
- Source available under [PolyForm Noncommercial 1.0.0](LICENSE). See [NOTICE](NOTICE).
- Memorizz is experimental: APIs may change and it has not undergone security
- hardening for production workloads.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.