obsei
Open source, privacy-first Voice of Customer analytics. A self-hosted alternative to Enterpret and Unwrap that strips PII from feedback before any LLM sees it.
No outside reports on file
Obsei reduces privacy risks by removing PII before AI processing, but it requires careful setup of data sources, secure credential storage, and monitoring to catch any leaks.
Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (obsei/obsei)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/obsei/obsei ↗
About Obsei
Obsei is a self-hosted tool that listens to customer feedback from various sources (like surveys, social media, and support tickets) and analyzes it using AI. Before any language model sees the feedback, it automatically removes personal information like names and email addresses to protect privacy.
Who it’s for
Companies that want to understand what customers think about their products but need to keep personal data private and avoid sending it to third-party services. It's designed for teams that prefer running tools on their own servers rather than using cloud-based analytics platforms.
Alternatives
- Enterpret: Commercial cloud-based Voice of Customer platform (what Obsei positions itself against).
- Unwrap: Enterprise feedback analytics tool (another cloud alternative Obsei mentions).
- Hugging Face Transformers with local models: DIY approach using open-source language models on your own hardware for sentiment and topic analysis.
- Apache Spark with NLP libraries: General-purpose data processing for customer feedback analysis on self-hosted infrastructure.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/obsei/obsei (opens external site) for installation and configuration instructions, as setup varies depending on your environment and feedback sources.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.4k
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Data collection scope: Can connect to many feedback sources (surveys, social media, ticketing systems), potentially accessing a wide range of customer information if misconfigured.
- PII removal reliability: The tool strips personal data before AI processing, but automated removal isn't perfect and sensitive information could sometimes slip through.
- Model prompt injection: Malicious feedback text could contain hidden instructions designed to manipulate the AI analysis or reveal how it works.
- Credential storage: Requires credentials to connect to feedback sources; if stored insecurely, attackers could access those connected accounts.
- AI model access: Depending on setup, feedback is sent to language models which may log or use the data according to their own policies.
How to lower the risk
Least-privilege permissions
- Grant only the minimum access needed to collect feedback from each source.
- Use separate credentials for Obsei that don't have admin rights to your customer systems.
Network isolation
- Run Obsei on your own infrastructure, not shared or untrusted networks.
- Restrict which services and APIs it can contact.
Monitoring
- Regularly check logs for unusual data access or failed PII removal.
- Audit which feedback sources are connected and what data flows through the system.
Red flags to watch for
- Credentials stored in plain text or default passwords left unchanged.
- Feedback containing sensitive data that wasn't removed by the PII filter.
- Unexpected network connections to unknown external services.
Questions
How do I install Obsei?
Obsei does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/obsei/obsei.
Are there security reports about Obsei?
No reports found for this package in our research (last checked 2026-10-29). Obsei currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include data collection scope, pii removal reliability, model prompt injection.
Is Obsei actively maintained?
Obsei has 1.4k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/obsei/obsei before pinning it in production.
What are alternatives to Obsei?
Notable alternatives to Obsei include Enterpret (Commercial cloud-based Voice of Customer platform (what Obsei positions itself against)), Unwrap (Enterprise feedback analytics tool (another cloud alternative Obsei mentions)), Hugging Face Transformers with local models (DIY approach using open-source language models on your own hardware for sentiment and topic analysis), Apache Spark with NLP libraries (General-purpose data processing for customer feedback analysis on self-hosted infrastructure). You can also compare Obsei side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Obsei? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/obsei-obsei)HTML embed:
<a href="https://agentarmorhq.com/skills/obsei-obsei"><img src="https://agentarmorhq.com/api/badge/obsei-obsei" alt="AgentArmorHQ Risk Grade for Obsei" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "obsei-obsei"Share with your security lead
Need sign-off to use obsei? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: obsei
- **Listing URL:** https://agentarmorhq.com/skills/obsei-obsei
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.4k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (obsei/obsei)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/obsei/obsei
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- obsei
- Source code
- github.com/obsei/obsei
- Est. context load
- ~900 tokens / turn (~5 tool schemas, 0.45% of 200k context)
- Popularity
- 1.4k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-22
Community
Discussions for Obsei
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude