Your AI agent should never see your API keys.

trustless keeps credentials out of agent context windows. Secrets are injected at the process layer, scrubbed from output, and masked in outbound traffic — the agent gets the API response, never the key.

Gozero dependenciessingle binaryMIT321 tests (-race)cosign-signed · SBOM
curl -fsSL https://raw.githubusercontent.com/ikkun1222/trustless/main/scripts/install.sh | sh

Linux / macOS · reads your existing pass or Bitwarden store — no migration, no new vault

Why trustless

AI coding agents (Claude Code, OpenCode, Codex) need API keys to call services. Traditional setups put those keys in .env files or the agent’s environment — which means the keys live inside the agent’s context window, where a prompt injection or an over-verbose debug log can leak them.

trustless reverses the model: the agent references a secret by name, and the broker resolves the value at the process or transport layer. The agent never holds the plaintext.

traditional:  agent → sees the key → uses the key → key in context → leak
trustless:    agent → says "use GITHUB_TOKEN" → broker resolves → agent gets the API response

Four layers

trustless run

Injects credentials as env vars into a subprocess, then sanitizes stdout/stderr — raw, base64, and URL-encoded key values never surface in agent-visible output.

trustless proxy

HTTP forward proxy with per-host header/query injection (EDINET, e-Stat, xAI, OpenRouter…). MITM mode for HTTPS. No config change in the agent.

trustless serve

Integrated DLP reverse proxy for any OpenAI-compatible endpoint. Outbound LLM calls are pattern-scanned (keyword → RE2 → entropy) and masked before leaving the machine. Hot-reloads on SIGHUP.

trustless dlp scrub

Prevention fails, so erasure exists. Two-layer redaction (known values + patterns) over session DBs and logs, with FTS rebuild + VACUUM — the bytes are actually gone, not hidden.

OAuth tokens (Google, Lark) are managed with automatic refresh, and every resolution lands in an append-only structured audit log (file or journald).

How it compares

The “keep secrets away from AI agents” space has several tools. trustless is the only one combining subprocess injection + output sanitization, an integrated outbound DLP, and existing password-manager backends in a single zero-dependency binary.

trustlesstenevaultyagent-secrets
Injectionsubprocess env + HTTP proxysubprocess envHTTP proxy + MCPsubprocess env (lease)
Existing backend (pass/Bitwarden)❌ own vault❌ own vault❌ own vault
Output sanitization✅ run + proxy
DLP (outbound redaction)✅ integratedpartial (request)
OAuth token management✅ (google/lark, refresh)
Dependencies0 (single binary)Go staticGo staticGo static
LicenseMITMITMITMIT

Comparison as of August 2026.

Why you can trust it

The full documentation, install options, and design documents live in the GitHub repository. Found a leak or a missing layer? Open an issue — this project's whole point is that the threat model is a moving target.