x18n reads the locale files of any project, finds where each key is used, and reports missing, unused and broken keys. A CLI, a language server, a VS Code extension, a UI and MCP tools share one engin
TraceRoot is an open-source, agent-native improvement layer for AI agents. Bring production traces, detector signals, and evals into your coding workflow.
Taiwan-built, self-hosted AI agent harness in a single Go binary — writes its own tools, sandbox-tests them, and shares them over MCP with Claude Code and Codex.
Sponsor: ProxyLane native static residential ISP IPs built for AI accounts: low Scamalytics fraud scores, a dedicated IP with unlimited traffic, from $3.90. Bind one IP per slot: paste the SOCKS5 line host:port:user:pass into 代理池 → 添加代理 (Proxy pool → Add proxy). Code VM2API30 gives 30% off your first purchase.
Traditional methods of converting AI subscriptions into API endpoints via simple reverse proxies frequently result in immediate account suspensions, stealth downgrades, and token corruption. vm2api is an enterprise-grade virtual machine gateway designed for ultra-reliable subscription-to-API infrastructure:
Universal Support: Seamlessly converts Anthropic (Claude Pro / Team / Enterprise / Max) and OpenAI (ChatGPT / Codex) subscriptions into robust standard APIs.
Genuine Client Process: Runs the authentic official Claude Code CLI system process inside an isolated VM / container instance instead of fragile HTTP emulation.
High-Fidelity Emulation: From physical SMBIOS, NIC MAC, and Machine-ID to dedicated per-slot network egress and pre-hop risk gates.
Standard Compatibility: Provides drop-in replacements for Anthropic /v1/messages and OpenAI /v1/chat/completions / /v1/responses.
Recent changes (1.3.133)
Since 1.3.122, the caller-visible changes are:
Telemetry reads only telemetry_disabled === false. The VM switch matches that bit and is on for the default; nonessential traffic and DNT follow it.
Intro docs sit to the right of GitHub in the console sidebar and open vm2api.fkcodex.com/zh.
Risk gates run before a slot is chosen: distill, hard regex, refusal cache, decision model, then egress. See below and docs/RISK.md.
Local proxy is the VPS that owns the slot. On a cluster node, ticket refresh, test chat, and geo also leave through that node. A disconnected node fails instead of falling back to the control plane.
Models are a card matrix. Haiku 5.5 defaults to a 100K context and output cap; an admin override is kept.
Keys can be limited to Anthropic or OpenAI and to selected slots. A call outside that scope returns 403.
Stream idle defaults to 180 seconds under retry settings. Long tool arguments can be streamed.
cli-node local delivery is now 2.1.303: share/wrap-cli/cli-node, 27,788,488 bytes after UPX, SHA256 efa72baab605c4ecee19a9e130b52ca2e1d6ef317880f5eaa5d90e867cc96aa4. Built from e30047ed plus the current working tree. The payload and live slots are unchanged.
No System Prompt Tampering: Unlike ordinary proxies that tamper with the system prompt and poison model identity, vm2api aligns credentials at the protocol layer as a genuine Console client.
Customizable Layouts: Switch effortlessly between zero (pure zero-injection), official, official_full, and tailored templates.
Transparent Benchmarks: Built-in benchmark suite guarantees no leaking of internal CLI tools or hidden instructions.
1️⃣ Physical Hardware Fingerprint Emulation
Eradicate Virtual Machine Artifacts: Supports containerized slots as well as genuine KVM/QEMU hypervisor nodes.
Comprehensive Hardware Spoofing: Simulates realistic hardware traits including SMBIOS identifiers, NIC MAC addresses, CPU architectures, system serials, and distinct /etc/machine-id.
2️⃣ Official Claude Code Native Process Forwarding & Slot Management
Authentic Official Binary Daemon: Every VM / container slot runs the authentic, official Claude Code binary daemon inside an isolated hypervisor sandbox. Requests are relayed via kernel-level Unix Domain Sockets, completely eliminating heuristic fingerprint leakage caused by custom reverse proxies.
Native 20-Subagent Concurrency per Slot: Each slot natively orchestrates up to 20 concurrent subagent threads with isolated conversation states and official prompt caching reuse.
5h / 7d Upstream Quota Alignment: Automatically aligns with Anthropic's rolling 5-hour and 7-day budget windows, calculating reset deadlines down to the minute. Integrates dynamic circuit breakers to gracefully divert traffic when a slot approaches its capacity limit.
Full Slot Lifecycle & Health Observability: Visual real-time tracking of slot states (In-Pool, Cooldown Guard, Suspended, Token Expired), multi-tier priority routing, and real-time per-slot financial cost accounting.
3️⃣ Pre-hop risk gates
/v1 and count_tokens pass the console Risk page (/console/#/risk) before any slot is chosen. A hit returns an error and does not spend upstream quota. The order is fixed:
Order
Gate
What it stops
Result
1
Distill
Harvest templates, problem fingerprints, and chain-of-thought extraction shapes. OpenAI platform models are skipped. Official Claude Code and zero-injection are skipped by default.
403, and the device is banned
2
Hard regex
NSFW, cracking, jailbreak, and custom patterns. Distill-category patterns follow the distill switch, not the hard-regex switch, and still scan official clients and zero-injection. OpenAI platform models skip that category.
403
3
Refusal cache
Exact text, similar text, and devices the upstream has already refused. Hard-regex and decision-model blocks are not stored here.
400, non-retryable, not a login failure
4
Decision model
A safety model scores the text and blocks only below the threshold. If scoring fails, the request is allowed by default and marked on the pass column.
403
5
Passed egress
Everything the gates allowed. The upstream's own refusals are listed separately, so a miss is visible.
Enters a slot
Open a hit and read the body. A false positive means tighten that gate, not delete the slot. Requests from before this recording show as unchecked. Full rules: docs/RISK.md.
4️⃣ Completely Isolated Network (1 VM = 1 Egress)
Zero Cross-Account Contamination: Every VM slot is strictly bound to its own dedicated SOCKS5 proxy or local egress gateway.
No Shared Egress: Prevents cascade bans caused by multiple accounts sharing the same outbound IP.
Custom HTTPS DoH: Supports custom DNS-over-HTTPS resolvers for stealthy and encrypted queries.
5️⃣ Deep Protocol Cleansing & Multi-Inbound Structuring
Multi-Protocol Inbound: Connect with Anthropic Messages API, OpenAI Chat format, or modern Responses API.
Structural Rectification: Normalizes invalid role sequences, corrects schema parameters, and translates inputs into clean payloads conforming to official client specifications.
6️⃣ Configurable Official Telemetry
Single-Machine Telemetry: Accurately simulates the telemetry signatures of a standalone physical workstation.
Granular Control: Operators can toggle and adjust telemetry forwarding based on operational privacy policies.
7️⃣ Multi-VPS Cluster Management
Agentless SSH Node Fleet: Connect and orchestrate multiple remote VPS hosts through lightweight, secure SSH connections.
Remote Docker Bridge: Effortlessly deploy, monitor, and place slot containers across different physical machines with built-in interactive web terminals (xterm).
8️⃣ Enterprise API Key & Quota Management
Multi-Tenant Security: Master key architecture with secondary HMAC-indexed tenant tokens.
Official Quota Alignment: Accurately tracks 5h/7d rolling budget windows, enforces rate limits (RPM/TPM), and provides seamless failover.
Comprehensive Telemetry & Observability: Real-time tracking of TTFT, genuine token consumption, SLA, and failure classifications.
Before opening an issue, follow ISSUE_GUIDE.md: version, reproduction steps, host/proxy environment, VM and request logs, optional source pointers — and redact all secrets.
