keygrant
No liveness check has reached it yet; it is registered on GitHub and PyPI and has been in the index since 8 Oct 2026. How this is checked
keygrant is an open-source command-line package for injecting secrets into individual commands used by AI coding agents. It is designed to keep secret values out of model context and supports workflows involving tools such as MCP and Claude Code.
Inferred · not functionally tested
Overview
5 featuresPurpose: Preventing secrets from entering AI coding agents' model context during command execution.
Inferred · not functionally tested
Audience: developers using AI coding agents
Inferred · not functionally tested
Functions: Unknown
Interfaces: API: unknown · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI, WEB · deployment: browser, cli, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: keygrant.app · github.com. These links do not verify the individual claims.
keygrant sits in PulseGate's AI & LLM security category. Inferred · not functionally tested: It focuses on preventing secrets from entering AI coding agents' model context during command execution. Inferred · not functionally tested: It is built as an open-source project for developers using AI coding agents. Basis unknown · not verified: The project is open source (Apache-2.0). Basis unknown · not verified: keygrant is available on the web and the command line, and it can be self-hosted.
Edward Bazinga builds and maintains keygrant, and it first shipped in 2026. Development happens publicly on GitHub with 20 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include per-command injection, secret isolation, and AI agent support. Basis unknown · not verified: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Per-command injection
- Secret isolation
- AI agent support
- MCP support
- Claude Code support
Topics: Inferred · not functionally tested
Built with & integrations
- Claude Code
- commit c622298efabf · since Oct 2026
Trust & compliance
Indexing history
2What PulseGate has recorded for this listing
Frequently asked questions about keygrant
- What is keygrant?
- Inferred · not functionally tested: Keygrant focuses on preventing secrets from entering AI coding agents' model context during command execution. It is catalogued under AI & LLM security on PulseGate.
- Who should use keygrant?
- Inferred · not functionally tested: keygrant is an open-source project built for developers using AI coding agents.
- Does keygrant have a free plan?
- Basis unknown · not verified: Yes — keygrant is open source under the Apache-2.0 license and free to use.
- What platforms does keygrant run on?
- Basis unknown · not verified: keygrant runs on the web and the command line. It can also be self-hosted.
- Is keygrant still active?
- The GitHub repository shows 20 commits in the last 90 days.
- Who develops keygrant?
- keygrant is developed by Edward Bazinga.
- How long has keygrant been around?
- keygrant first shipped in 2026.
- Is keygrant open source?
- Basis unknown · not verified: Yes — keygrant is open source under the Apache-2.0 license, developed on GitHub.
Similar projects
Closest matches by what these projects do