kody
🐨 The cloud for your team's agents. Save your agent memory, credentials, code, and automations, portable across every agent with Kody.
No outside reports on file
Kody consolidates sensitive agent data and credentials in one place, making it a high-value target that could expose everything across your agent ecosystem if compromised.
Based on public adoption and transparency signals as of Oct 24, 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 sourcenpm (@kodycodes/cli)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y @kodycodes/cliEverything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-24.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Kody
Kody is a cloud platform that stores and manages agent memory, credentials, code, and automation workflows. It lets AI agents across different systems access shared information and configurations from one central place.
Who it’s for
Teams running multiple AI agents who need a shared storage system for credentials and settings. Developers building agent-based automation who want portable configurations across different agent platforms.
Alternatives
- HashiCorp Vault: Open-source secrets management with strong access controls and audit trails.
- AWS Secrets Manager: Cloud-native credential storage with fine-grained permissions and encryption.
- CyberArk Conjur: Enterprise secret management designed for automated systems and agents.
- 1Password for Teams: Team credential sharing with encryption and activity monitoring.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/kody-hq/kody (opens external site) for installation and configuration instructions, as the setup process depends on your deployment environment.
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
- 868
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Credential storage: Stores authentication tokens and secrets centrally, so a breach exposes credentials across all connected agents.
- Agent memory access: Agents can retrieve and potentially misuse sensitive historical data or patterns stored about your team.
- Code execution risk: Custom automations and code stored in Kody could be modified by attackers to run malicious commands on connected systems.
- Data leakage through summaries: AI agents might accidentally include sensitive stored data in responses or logs if not carefully configured.
- Centralized trust: All agents depend on this one service; if compromised, attackers gain access to all agent configurations and secrets at once.
How to lower the risk
Least-privilege permissions
- Grant agents only the specific credentials and memory sections they need.
- Use role-based access to limit which team members can modify stored automations.
Network isolation
- Run Kody in a private network or VPC if possible, not directly on the public internet.
- Restrict API access to known agent IP addresses or authentication tokens.
Monitoring
- Log all credential access and data retrievals to detect unusual patterns.
- Alert on any changes to stored code or automation workflows.
Red flags to watch for
- Agents requesting credentials they don't normally need.
- Unexpected changes to automation code without your approval.
- Failed login attempts or unusual access times from unfamiliar locations.
Questions
How do I install Kody?
Run npx -y @kodycodes/cli in your terminal, or add the server entry to your claude_desktop_config.json or .cursor/mcp.json as shown in the Setup section on this page. Full setup docs and environment variables are in github.com/kody-hq/kody.
Are there security reports about Kody?
No reports found for this package in our research (last checked 2026-10-30). Kody currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include credential storage, agent memory access, code execution risk.
Is Kody actively maintained?
Kody has 868 GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/kody-hq/kody before pinning it in production.
What are alternatives to Kody?
Notable alternatives to Kody include HashiCorp Vault (Open-source secrets management with strong access controls and review trails), AWS Secrets Manager (Cloud-native credential storage with fine-grained permissions and encryption), CyberArk Conjur (Enterprise secret management designed for automated systems and agents), 1Password for Teams (Team credential sharing with encryption and activity monitoring). You can also compare Kody side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Kody? 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/kody-hq-kody)HTML embed:
<a href="https://agentarmorhq.com/skills/kody-hq-kody"><img src="https://agentarmorhq.com/api/badge/kody-hq-kody" alt="AgentArmorHQ Risk Grade for Kody" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "kody-hq-kody"Share with your security lead
Need sign-off to use kody? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: kody
- **Listing URL:** https://agentarmorhq.com/skills/kody-hq-kody
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 868 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:** npm (@kodycodes/cli)
#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts @kodycodes/cli`
- **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 24, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- kody-hq
- Source code
- github.com/kody-hq/kody
- Install command
- npm install @kodycodes/cli
- Est. context load
- ~550 tokens / turn (~3 tool schemas, 0.27% of 200k context)
- Popularity
- 868 GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-24
Community
Discussions for Kody
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