Agentkms — AI skill for Claude Code
Cryptographic proxy and credential vending for LLM applications.
How to install Agentkms
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open TheGenXCoder/agentkms and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agentkms does
Cryptographic proxy and credential vending for LLM applications. Zero secrets on disk. mTLS everywhere. Apache 2.0.
Alternatives in AI
- Opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama… 12.3k ★
- Osaurus — Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cry 5.1k ★
- WindsurfAPI — Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, A 3k ★
README
AgentKMS
**AgentKMS is the secret-issuing authority for AI coding agents.** It vends scoped, short-lived credentials, enforces policy, and produces a forensic chain-of-custody when credentials leak.
Stop putting LLM API keys in `.env` files.
Quick Start (local dev — 5 minutes)
**Unified binary** (v0.6.0+):
git clone https://github.com/TheGenXCoder/agentkms.git
cd agentkms
go build -o agentkms ./cmd/agentkms
agentkms init --dev
agentkms serve
**Legacy dev binary** (still supported):
go build -o agentkms-dev ./cmd/dev/
./agentkms-dev enroll
./agentkms-dev serve
# Verify
curl -sk https://localhost:8443/healthz
Store secrets and fetch them
# Authenticate — uses client cert from ~/.agentkms/dev/
TOKEN=$(curl -s \
--cert ~/.agentkms/dev/clients/default/client.crt \
--key ~/.agentkms/dev/clients/default/client.key \
--cacert ~/.agentkms/dev/ca.crt \
-X POST https://127.0.0.1:8443/auth/session | jq -r .token)
# Fetch a credential
curl -s \
--cert ~/.agentkms/dev/clients/default/client.crt \
--key ~/.agentkms/dev/clients/default/client.key \
--cacert ~/.agentkms/dev/ca.crt \
-H "Authorization: Bearer $TOKEN" \
https://127.0.0.1:8443/credentials/llm/anthropic
# {"provider":"anthropic","api_key":"sk-ant-...","expires_at":"...","scope":"..."}
Use It in Claude Code (30 seconds)
// Add to your Claude Code MCP settings:
{
"mcpServers": {
"agentkms": {
"command": "agentkms-mcp"
}
}
}
That's it. Claude Code can now securely fetch LLM keys, sign payloads, and encrypt data — all over mTLS, zero secrets on disk. Also works with **Cursor**, **Windsurf**, and any MCP-compatible tool.
Architecture
AI Tool (Claude Code, Cursor, Windsurf)
↓ MCP (stdio JSON-RPC)
agentkms-mcp (local binary, cmd/mcp)
↓ mTLS
AgentKMS (laptop / corp VPC, cmd/server or cmd/dev)
↓ plugin API (gRPC, api/plugin/v1/plugin.proto)
dynsecrets-github | dynsecrets-aws | comm
Related Skills
Residoo
Find secrets your AI coding agent leaked to disk. Free, MIT, zero deps, zero network calls. Beat TruffleHog an
Straylight AI
Zero-knowledge credential proxy for AI agents. Use AI, with Zero trust.
PrivAiTe
Self-hosted PII redaction proxy for LLM APIs and agent CLIs. Scrubs names, emails and secrets from Claude Code
Keyfence
Local proxy that keeps your API keys and secrets out of LLM requests. Works with Claude Code, Cursor, Codex an
Fraction
Persistent memory layer for LLM agents and AI applications. Zero API costs, sub-100ms ingestion, fully offline
LLM Secret Manager
The secret manager for LLM agents: create, rotate, and use secrets they can never read. OS-native keyvault (ma
Related Agents
Dotnet Security Reviewer
WHEN reviewing .NET code for security vulnerabilities, OWASP compliance, secrets exposure, or cryptographic mi
Light Security ClaudeSettingsAudit
Audit Claude Code config files (settings.json, settings.local.json, .mcp.json) for unsafe or malicious content
De Kafka Expert
Expert Apache Kafka developer for event streaming, topic design, and producer-consumer patterns. Use for Kafka