My Brain Is Full - Crew Last updated: 2026-03-23
By using this software, you agree to the following terms. If you do not agree, do not use the software.
This software is a collection of AI agent prompts ("the Crew") designed to help individuals organize personal notes, tasks, and information inside an Obsidian vault using Claude Code. It is an open-source tool provided free of charge under the MIT License.
The software does not collect, transmit, or store any data outside your local device. All data remains in your Obsidian vault on your filesystem.
This software is designed and intended exclusively for personal, non-commercial use on your own data. It is not designed for:
- Professional or commercial data processing
- Use by organizations, companies, or teams on behalf of third parties
- Processing of data belonging to other individuals without their knowledge and consent
- Any use that would qualify you as a "data controller" or "data processor" under applicable law without the appropriate legal basis and safeguards in place
If you choose to use this software outside the scope of personal use, you do so entirely at your own risk and responsibility.
This software allows users to create custom agents (see Section 9) that may generate output in domains including, but not limited to: health, nutrition, fitness, diet, mental wellness, legal matters, financial planning, tax strategy, investment, career guidance, parenting, relationship advice, and any other area where professional expertise would normally be required.
By using any agent — core or custom — that produces advice-like output, you explicitly acknowledge and accept that:
a) All agents produce AI-generated output only. They are not medical devices, medical software, health apps, therapeutic tools, legal counsel systems, financial advisory platforms, or professional service tools within the meaning of any applicable regulation or professional licensing framework.
b) The output of any agent does not constitute medical advice, nutritional counseling, dietary prescription, psychological therapy, psychiatric treatment, legal advice, legal opinion, financial advice, investment recommendation, tax guidance, or any other form of professional counsel or service, regardless of how specific, detailed, or authoritative the output may appear.
c) The author of this software is not a healthcare professional, licensed therapist, registered dietitian, medical practitioner, attorney, licensed financial advisor, certified public accountant, or any other licensed or regulated professional of any kind. The author provides prompt engineering only.
d) All output that resembles professional advice — including but not limited to calorie calculations, TDEE estimates, meal plans, dietary suggestions, therapeutic techniques, mood assessments, legal interpretations, contract analyses, financial projections, investment strategies, tax calculations, and any other domain-specific guidance — is approximate, potentially inaccurate, potentially outdated, and not validated by any medical, legal, financial, scientific, or regulatory authority.
e) You must not rely on any agent as your sole or primary source of information in any domain where professional expertise is normally required. You must consult qualified, licensed professionals for all health-related, legal, financial, and other regulated decisions.
f) If you have or suspect you have a medical condition, eating disorder, mental health crisis, or any health emergency, you must immediately contact a qualified healthcare provider or emergency service. If you face a legal emergency or time-sensitive legal matter, you must immediately consult a licensed attorney in your jurisdiction. These agents are not equipped to handle emergencies of any kind.
g) You voluntarily assume all risk associated with following any suggestion, plan, technique, interpretation, or recommendation generated by any agent, whether core or custom.
h) The author accepts no liability whatsoever for any harm, injury, illness, deterioration of health, psychological distress, financial loss, legal consequence, regulatory penalty, missed deadline, or any other adverse outcome resulting from your use of any agent's output, whether directly or indirectly.
i) Custom agents are entirely user-created. The author has no control over, knowledge of, or responsibility for the prompts, domains, or behaviors of custom agents. Any custom agent that produces advice-like output is subject to all the disclaimers in this section, regardless of whether the user explicitly acknowledges it at creation time.
This software can access your email inbox (Gmail via the Google Workspace CLI or MCP connectors, Hey.com via the Hey CLI) and Google Calendar, and may save content from those sources as notes inside your local Obsidian vault.
You are solely responsible for:
a) Ensuring that your use of this software complies with all applicable privacy and data protection laws, including but not limited to:
- The EU General Data Protection Regulation (GDPR), Regulation (EU) 2016/679
- The California Consumer Privacy Act (CCPA), Cal. Civ. Code § 1798.100 et seq.
- The UK Data Protection Act 2018
- Any other national, regional, or sector-specific data protection legislation applicable to you
b) Obtaining all necessary consents and establishing a lawful basis before processing any personal data of third parties through this software.
c) Implementing appropriate technical and organizational measures to protect any personal data processed through this software, including but not limited to encryption, access controls, retention policies, and data subject rights mechanisms.
d) Responding to any data subject access requests, deletion requests, or other rights exercised by individuals whose data you process through this software.
Emails and calendar events contain personal data of other people (names, email addresses, phone numbers, meeting content, personal communications). When the Postman agent reads your inbox and saves content to your vault:
- That data is stored in plaintext on your local filesystem
- You become the data controller for that data under applicable law
- You are responsible for ensuring a lawful basis for that processing
- You are responsible for informing those individuals that their data is being processed, if required by law
- You are responsible for deleting that data upon request, if required by law
The author of this software:
- Is not a data controller or data processor with respect to any data you process
- Has no access to your vault, emails, calendar, or any data you process
- Does not collect, receive, store, or transmit any of your data or any third-party data
- Cannot respond to data subject requests on your behalf
- Accepts no liability for any data protection violations arising from your use of this software
This software can perform read and write operations on your email inbox (Gmail and/or Hey.com) and Google Calendar, including but not limited to:
Read operations: searching emails, reading email content and threads, listing calendar events, reading event details.
Write operations on email (when the Google Workspace CLI or Hey CLI is installed): archiving emails, deleting/trashing emails, marking emails as read/unread (or seen/unseen in Hey), adding and removing labels, sending emails, replying to threads, creating email drafts. Write operations on Google Calendar (when the Google Workspace CLI is installed): creating calendar events, modifying calendar events, deleting calendar events.
When the software reads your emails and calendar events:
a) Email and calendar content is processed by the underlying AI model. The AI model is a stochastic system (see Section 5) and may misinterpret, misclassify, or hallucinate information from your emails. The software may create vault notes that contain inaccurate summaries, wrong dates, fabricated action items, or misattributed quotes.
b) Emails may contain adversarial content (prompt injection, social engineering, phishing) designed to manipulate AI systems. While the software includes prompt-level defenses against such attacks, prompt-based security is best-effort, not a guarantee. The author cannot guarantee that the AI model will correctly ignore adversarial instructions embedded in email content under all circumstances.
c) Sensitive information from emails (personal data, financial details, confidential communications, passwords, tokens, API keys) may be inadvertently saved to vault notes in plaintext. You are responsible for reviewing what the software saves.
When the software performs write operations on your Gmail or Google Calendar:
a) Sending emails: The software may compose and send emails on your behalf. An email sent by the software is indistinguishable from an email you sent yourself. The author accepts no responsibility for the content, tone, accuracy, appropriateness, or consequences of any email sent by the software, including but not limited to: emails sent to wrong recipients, emails with incorrect information, emails with inappropriate tone or content, and emails that cause professional, personal, legal, or financial harm.
b) Archiving, deleting, or modifying emails: The software may archive, trash, delete, label, or mark emails as read. These operations may cause you to miss important emails, deadlines, or communications. Deleted emails may be unrecoverable. The author accepts no responsibility for any email that is lost, archived prematurely, mislabeled, or otherwise modified in a way that causes harm.
c) Calendar modifications: The software may create, modify, or delete calendar events. This may result in missed meetings, scheduling conflicts, double-bookings, deleted events, or events created with incorrect details (wrong date, time, participants, or location). The author accepts no responsibility for any scheduling disruption caused by the software.
d) Adversarial email content triggering write actions: Despite prompt-level security measures, a malicious or adversarial email could potentially manipulate the AI model into performing unintended write operations — such as sending a reply, forwarding content, archiving important emails, creating calendar events, or deleting messages. The author cannot guarantee that prompt-based defenses will prevent all such scenarios. You assume full responsibility for all actions performed by the software on your email and calendar accounts.
By enabling email and calendar access, you explicitly acknowledge and accept that:
a) You have reviewed and understood the risks described in this section before granting the software access to your email and calendar accounts.
b) You are solely responsible for monitoring and reviewing all actions the software performs on your email and calendar accounts, including emails sent, emails archived or deleted, labels applied, and calendar events created, modified, or deleted.
c) You should regularly check your Sent folder, Trash, and Calendar to verify that the software has not performed unintended actions.
d) The software's prompt-level security measures (instructions to ignore adversarial content, confirmation gates before write operations) are best-effort safeguards, not guarantees. They depend on the underlying AI model correctly following instructions, which cannot be assured in all cases.
e) You voluntarily assume all risk associated with granting the software read and write access to your email and calendar accounts, including the risk of data loss, unintended communications, missed messages, and scheduling disruptions.
f) The author accepts no liability whatsoever for any harm, loss, or damage resulting from the software's email and calendar operations, whether caused by AI misinterpretation, adversarial content, software bugs, model hallucination, or any other reason.
This software provides prompts and instructions to large language models (LLMs). The author does not provide, host, train, fine-tune, or control any AI model. All output is generated by the underlying LLM at runtime.
You explicitly acknowledge and accept that:
a) Large language models are stochastic systems. They generate output probabilistically. The same input can produce different output on different runs. Output may contain errors, fabrications, contradictions, or nonsensical content at any time, without warning.
b) LLMs can and do hallucinate: they generate text that appears factual but is partially or entirely fabricated. This includes invented facts, false citations, incorrect calculations, non-existent references, and plausible-sounding but wrong information.
c) The author provides prompt engineering only. The behavior, accuracy, safety, and reliability of the output depend entirely on the underlying model, its training data, its alignment methods (RLHF, DPO, Constitutional AI, or others), its safety filters, and its runtime configuration. The author has no control over any of these factors.
d) This software is designed and tested with Anthropic's Claude models. If you use a different LLM (whether through a fork, a plugin modification, a different MCP configuration, or any other means), the quality, safety, and reliability of the output are entirely unpredictable and entirely your responsibility. Models without adequate alignment, safety training, or content filtering may produce harmful, misleading, dangerous, or offensive output.
e) Even when using Claude, no output should be treated as authoritative, factual, or reliable without independent verification. This applies to all agents — core and custom — including but not limited to: factual claims made by the Seeker, organizational suggestions by the Architect, and any advice-like output generated by custom agents in domains such as health, legal, financial, or any other regulated field.
f) Even though this software has been tested by the author using Anthropic's Claude, no quality standard can be guaranteed. Due to the inherent stochastic nature of large language models, the same prompt can produce different output across different sessions, model versions, context windows, and runtime conditions. Testing validates that the prompts are well-formed and produce reasonable results under observed conditions, but it cannot and does not guarantee consistent, accurate, or safe output in all circumstances or for all users.
The author:
- Does not guarantee the accuracy, completeness, safety, or appropriateness of any output generated by any agent under any circumstances
- Does not guarantee that safety instructions in the prompts will be followed by the model in all cases. Prompt-based safety is best-effort, not a guarantee
- Does not guarantee that the software will behave identically across different model versions, providers, or configurations
- Is not responsible for any output generated by models other than Anthropic's Claude, regardless of the reason the user chose to use a different model
- Is not responsible for any action you take based on AI-generated output
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND NONINFRINGEMENT.
The author does not warrant that:
- The software will function correctly, without errors, or without interruption
- The output of any agent will be accurate, complete, or appropriate
- The software will not cause data loss or corruption in your vault
- The software is suitable for any particular purpose
IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT, OR OTHERWISE, ARISING FROM, OUT OF, OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
This includes, without limitation, liability for:
- Any advice-like output generated by core or custom agents, including but not limited to health, legal, financial, dietary, and wellness domains
- Hallucinated, fabricated, inaccurate, or misleading content generated by the underlying AI model
- Any consequence of using this software with a model other than Anthropic's Claude
- Loss or corruption of data in your vault
- Violations of data protection law arising from your use of the software
- Any action taken by custom agents created by the user (Section 9)
- Emails sent, forwarded, or replied to by the software, including emails with incorrect content, wrong recipients, or inappropriate tone
- Emails archived, deleted, trashed, labeled, or marked as read by the software, including missed communications resulting from premature archival or deletion
- Calendar events created, modified, or deleted by the software, including missed meetings, scheduling conflicts, or events with incorrect details
- Any action triggered by adversarial or malicious email content that manipulates the AI model into performing unintended operations, despite prompt-level security measures
- Any indirect, incidental, special, consequential, or punitive damages
- Loss of profits, data, goodwill, or other intangible losses
The author takes no responsibility for forks, modifications, or derivative works of this software. If a third party modifies this software and distributes it, the modified version is governed by the third party's own terms, not these.
The author explicitly condemns any use of this software or its derivatives for: unauthorized data collection, psychological manipulation, impersonation of medical or mental health professionals, surveillance, or any form of exploitation or harm.
This software allows users to create custom AI agents through the Architect agent. Custom agents are user-generated prompt configurations stored in the user's vault.
By creating and using custom agents, you explicitly acknowledge and accept that:
a) Custom agents are entirely your creation and your responsibility. The author of this software has no involvement in their design, behavior, or output.
b) The author provides no warranty whatsoever on the functionality, accuracy, safety, or reliability of any custom agent you create, regardless of whether the Architect agent assisted in generating the agent file.
c) You are solely responsible for everything your custom agents do, including but not limited to: what data they read, what notes they create, what files they modify, what information they process, and any consequences of their actions.
d) Custom agents are subject to the same limitations described in Section 5 (AI-Generated Output and Model Limitations). They produce stochastic, probabilistic output that may be inaccurate, incomplete, or misleading.
e) The author accepts no liability for any harm, data loss, privacy violation, or any other adverse outcome resulting from the use of custom agents, whether directly or indirectly.
f) If you share your custom agents with others (through forks, exports, or any other means), Section 8 (Forks, Modifications, and Derivative Works) applies in full. You become responsible for the shared agent's behavior.
These terms are governed by and construed in accordance with the laws of the jurisdiction in which the author resides, without regard to conflict of law principles. Any disputes arising from these terms or the use of the software shall be subject to the exclusive jurisdiction of the courts of that jurisdiction.
The author reserves the right to modify these terms at any time. Changes will be reflected in the Last updated date at the top of this document. Continued use of the software after changes constitutes acceptance of the updated terms.
By using this software (including by running the installer, loading the plugin, or interacting with any agent), you confirm that you have read, understood, and agree to these Terms of Use.
If you create or use any custom agent that generates advice-like output in regulated domains (health, legal, financial, dietary, wellness, or similar), you additionally confirm that you have read and accepted the disclaimers in Section 3 above, and that you understand these disclaimers apply automatically to all such agents.