Secret

Secrets management for teams and AI agents.

Security operations toolkit for AI coding agents. Give Claude Code 25+ skills to catch vulnerabilities, scan containers, detect secrets, and enforce policies automatically.

All-in-one Kubernetes SDK: create, manage, and operate clusters across distributions (Kind, K3d, Talos, VCluster) with built-in GitOps, secrets, AI assistant, and MCP server. Only requires Docker or a Cloud Provider.

AI Agent Lockout Backup Kit A vendor-independent continuity kit for backing up, rotating, and recovering information used by AI agents—without storing secrets in the agent or in GitHub. Check out Muse, your personal AI agent. Code: 5F2V31 https://muse.ai/join

Like ChatGPT's voice conversations with an AI, but entirely offline/private/trade-secret-friendly, using local AI models such as LLama 2 and Whisper

Ghost Security's Skills Marketplace supercharges Claude Code to be an application security expert in code security analysis, dependency/secrets scanning, and dynamic vulnerability testing

Security guardrails for Claude Code, MCP tools, and Claude cowork workflows. Local-first modular YARA-style guard packs for secrets, exfiltration, prompt injection, MCP abuse, and risky agent actions.

Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.

Local-first identity, memory, and secrets for AI agents. Portable state across models and harnesses.

Portable snapshot of a pi coding-agent setup + backup/restore tooling. Clone to rebuild 22 extensions on another machine. Excludes secrets, cache, and machine state.

Local-first MCP gateway. Set up MCP servers once and use them in every AI client, with secrets in the OS keychain, tool integrity checks and quarantine, and on-demand tool search for clients that load every tool.

The local firewall for AI agents — keep your secrets off the model, the API relay, and the supply chain. Local credential masking, per-route model routing, and security detectors on the wire. Free & fully open source.

Open-source Python, TypeScript, and Go SAST with dead code detection. Finds secrets, exploitable flows, and AI regressions. VS Code extension, GitHub Action, and MCP server for AI agents.

🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.

Turn a fresh LXC into an AI homelab command center. One command installs Claude Code + a web UI, preloaded with skills, and a credential broker so Claude operates your TrueNAS/Proxmox/Linux over SSH without ever seeing a secret.

Your local AI session library. Browse, pin, and ⌘K-search every Claude Code, Codex, Gemini & OpenCode session — and let the built-in scanner catch leaked secrets. Local-first, nothing leaves your machine.

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

Skip to content github / docs Code Issues 80 Pull requests 35 Discussions Actions Projects 2 Security Insights Merge branch 'main' into 1862-Add-Travis-CI-migration-table 1862-Add-Travis-CI-migration-table (#1869, Iixixi/ZachryTylerWood#102, THEBOLCK79/docs#1, sbnbhk/docs#1) @martin389 martin389 committed on Dec 9, 2020 2 parents 2f9ec0c + 1588f50 commit 1a56ed136914e522f3a23ecc2be1c49f479a1a6a Showing 501 changed files with 5,397 additions and 1,362 deletions. 2 .github/allowed-actions.js @@ -30,7 +30,7 @@ module.exports = [ 'rachmari/labeler@832d42ec5523f3c6d46e8168de71cd54363e3e2e', 'repo-sync/github-sync@3832fe8e2be32372e1b3970bbae8e7079edeec88', 'repo-sync/pull-request@33777245b1aace1a58c87a29c90321aa7a74bd7d', 'rtCamp/action-slack-notify@e17352feaf9aee300bf0ebc1dfbf467d80438815', 'someimportantcompany/github-actions-slack-message@0b470c14b39da4260ed9e3f9a4f1298a74ccdefd', 'tjenkinson/gh-action-auto-merge-dependency-updates@cee2ac0', 'EndBug/add-and-commit@9358097a71ad9fb9e2f9624c6098c89193d83575' ] 72 .github/workflows/confirm-internal-staff-work-in-docs.yml @@ -0,0 +1,72 @@ name: Confirm internal staff meant to post in public on: issues: types: - opened - reopened - transferred pull_request_target: types: - opened - reopened jobs: check-team-membership: runs-on: ubuntu-latest continue-on-error: true if: github.repository == 'github/docs' steps: - uses: actions/github-script@626af12fe9a53dc2972b48385e7fe7dec79145c9 with: github-token: ${{ secrets.DOCUBOT_FR_PROJECT_BOARD_WORKFLOWS_REPO_ORG_READ_SCOPES }} script: | // Only perform this action with GitHub employees try { await github.teams.getMembershipForUserInOrg({ org: 'github', team_slug: 'employees', username: context.payload.sender.login, }); } catch(err) { // An err

Self-hosted orchestrator for AI autonomous agents. Run Claude Code & Open Code in isolated linux workspaces. Manage your skills, configs and encrypted secrets with a git repo.

SWE-ATLAS turns Claude Code into a senior AI software engineer agent: multi-project workspaces with memory, wireframe & prototype first planning, secrets kept out of chat, psql, browser QA runners, and CI/CD-aware deploys. One command: npx swe-atlas new-project

Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

Quality gate for AI/Codex-generated pull requests: blocks TODO leftovers, leaked secrets, sloppy commits and red CI before they reach main.

Open-source, multi-platform harness for AI agents - a native, multi-threaded operator's console (JVM, not Electron) to run Claude Code, Codex, Gemini or OpenCode with a real browser, terminal, editor, secrets & 200+ MCP tools. Built for enterprises, science & research.

Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.