✨ Winx — Remote MCP Runtime for Coding Agents

Winx is a remote-first MCP runtime for agents that need a real shell, guarded file-editing primitives, repository-aware code navigation, and sessions that survive dropped connections. Its primary deployment path is a hardened Streamable HTTP endpoint for ChatGPT and other cloud or networked MCP clients; stdio remains fully supported for Claude Code, Codex CLI, Cursor, VS Code, and other local clients.

On Unix, Winx separates the MCP adapter from the processes that own each PTY. winxd manages the control plane and one winx-guardian per logical session keeps the shell alive across HTTP disconnects, client restarts, and adapter upgrades. It started as a Rust port of WCGW, but it is not a Python wrapper: cd persists, Ctrl+C interrupts the real process, interactive TUIs work, and large terminal output is rendered and token-budgeted before reaching the model.

[!IMPORTANT] Streamable HTTP is the main deployment path. Winx binds it to loopback by default, requires a strong bearer token, supports independent authenticated principals, and defaults to one durable session per principal/workspace. Repeated stateless Initialize calls reattach instead of manufacturing a new guardian.

Remote MCP in 60 seconds

cargo install winx-code-agent

mkdir -p ~/.config
install -m 600 /dev/null ~/.config/winx-http-token
openssl rand -hex 32 > ~/.config/winx-http-token

winx-code-agent serve --http \
  --bind 127.0.0.1:8000 \
  --token-file ~/.config/winx-http-token

Connect an MCP client to:

http://127.0.0.1:8000/mcp
Authorization: Bearer <contents of ~/.config/winx-http-token>

Cloud clients need a reachable HTTPS endpoint. Keep Winx on loopback and use a private MCP tunnel, VPN, or authenticated HTTPS reverse proxy in front. For OpenAI products, the Secure MCP Tunnel keeps Winx private while exposing an OpenAI-hosted MCP endpoint.

Next: complete Streamable HTTP deployment guide · security model · local stdio setup

Why Winx for remote agents

• Durable sessions: HTTP is stateless from the client's point of view, but Unix PTYs live in per-session guardians and can be resumed with the same thread_id.
• Identity-aware isolation: one token per principal; thread IDs and MCP Task IDs are scoped internally and translated back before the response leaves the server. Workspace affinity absorbs unstable model-generated thread IDs.
• Fail-closed network defaults: loopback-only binding, 32-byte minimum tokens, chmod-600 token files, DNS-rebinding host checks, body/time/concurrency limits, per-IP rate limiting, and delayed invalid-auth responses.
• Agent-native terminal semantics: foreground and background commands, status polling, interactive input, stable TUI snapshots, turn detection, real exit codes, and bounded output.
• Repository tools, not just a shell: guarded SEARCH/REPLACE edits, multi-file planning, undo, token-budgeted reads, image input, context handoff, and tree-sitter symbol navigation.

Choose your transport

Transport	Best for	Endpoint / launch	Authentication	Session model
Streamable HTTP	ChatGPT, hosted agents, remote automation, multiple MCP clients	https://host/mcp through a tunnel/proxy, with Winx on 127.0.0.1:8000	Strong bearer token; optional multi-principal TOML	Stateless requests mapped to durable principal/workspace sessions by default
stdio	Claude Code, Codex CLI, Cursor, VS Code, desktop and local IDE clients	client launches winx-code-agent	Local process boundary	One local client, using the same durable daemon runtime on Unix

Remote architecture

Remote MCP client
       │  HTTPS + bearer token
       ▼
Secure MCP Tunnel / VPN / authenticated reverse proxy
       │  loopback HTTP
       ▼
127.0.0.1:8000/mcp
       │
       ├─ Host / body / timeout checks
       ├─ Per-IP rate limit + global concurrency cap
       ├─ Principal authentication
       └─ thread_id and MCP Task scoping
              │
              ▼
        shared WinxService
              │
              ▼
            winxd
              │
              └─ winx-guardian per session ── real PTY / shell / TUI

What you get

• A stateful bash session per thread with proper PTY semantics - foreground, background, status checks, text input, Enter/Ctrl-C/Ctrl-D, raw ASCII. Multiline scripts and top-level command shorthand both work; NUL bytes are rejected before they reach the shell.
• Workspaces with three modes: wcgw (full access), architect (read-only), code_writer (allowlist of commands and write globs). The command allowlist is parsed with tree-sitter, so it checks every command on the line - pipelines, &&/||/;, command substitution, subshells - not just the first word, and can't be bypassed with ls && curl … | sh or ls $(rm …).
• A resilient PTY: a shell that won't return to a prompt (even after Ctrl-C) is auto-reset at the same cwd/mode, child processes are reaped on drop, and prompt detection is robust to a custom PS1. Opt into zsh with WINX_SHELL=zsh.
• File reads with WCGW-style line ranges (file.rs:10-40, file.rs:10-, file.rs:-40). Active files are tracked and prioritized in the repository context across calls.
• File writes and SEARCH/REPLACE edits that survive ambiguous matches, indentation drift, and the usual unicode quote-mismatches from LLMs. Writes are blocked when the file hasn't been read or the cached content is stale, the success message shows a compact diff of what changed, and recent edits are reversible with UndoEdit. MultiFileEdit validates and computes every file before writing any of them, so a validation failure on the last file leaves the earlier ones untouched. The commit phase uses atomic per-file renames; a rare mid-commit I/O failure stops immediately but does not roll back files already written.
• Tree-sitter code navigation via CodeMap: a token-budgeted symbol map of a file or the whole repo, or a definition/reference lookup for a symbol name - the semantic view that plain grep can't give you, across 11 languages.
• ContextSave for handing a task summary plus its files to the next session - including workspace context, active files, git status/diff, and terminal sharing for proper resumption. Resuming reopens the saved project root and token-caps the restored memory so it never overflows the context window.
• ReadImage so multimodal clients can pull screenshots, mockups, error PNGs, etc.
• Clean, token-aware shell output: cursor/ANSI noise from interactive programs (REPLs, progress bars) is rendered away through a terminal emulator, and mechanical repetition is collapsed losslessly (line [winx: ×N]) so build/install logs don't blow your context budget. Toggle the collapsing with WINX_NO_COMPRESS. When output still overflows the cap, the dropped head is streamed to a scratch file under .winx/scratch/ the agent can re-read, instead of being lost.
• Secret redaction on by default: provider API keys, JWTs, PEM private-key blocks and user:pass@ URLs are scrubbed from all tool output and saved memory before they reach the model (disable with WINX_NO_REDACT=1). An opt-in Landlock sandbox (WINX_SANDBOX=1, Linux) adds a kernel-enforced second layer that confines writes to the workspace and hides the home directory.
• A hardened Streamable HTTP endpoint (winx-code-agent serve --http) for remote MCP clients, with stdio retained for local tools. HTTP binds to loopback by default, requires a strong bearer token, limits request size/rate/concurrency, and isolates sessions and MCP Tasks across authenticated principals - see the deployment guide.

MCP Tools

Tool	What it does
Initialize	Boots the workspace, picks the mode, hands you a thread_id. Call this first unless a local MCP client exposes Roots, in which case Winx can bootstrap the workspace automatically. With no workspace path it spins up a scratch playground; resuming a task (task_id_to_resume) reopens its saved project root.
BashCommand	Runs commands, polls long-running ones, sends Enter/Ctrl-C, drives TUIs. Supports is_background, status_check, send_text, send_specials, send_ascii, allow_multi, plus screen (a stable point-in-time frame of an interactive TUI with the cursor position; pass diff:true for only the lines that changed since your last look) and wait_for_turn (block until the TUI is ready for input, via per-app or configurable recognizers). A foreground command also supports MCP Tasks: task calls return immediately, remain pollable through tasks/get, can be cancelled, and retain the final CallToolResult for tasks/result. When a foreground command finishes, the status line reports its real exit code (parsed from the prompt marker), so failures surface without grepping stderr.
ReadFiles	One or many files, with line numbers. Append :10-40 to a path for a range. When the token budget is hit it tells you the exact line + file:N-M syntax to resume from instead of silently dropping the tail.
FileWriteOrEdit	Full overwrites or SEARCH/REPLACE blocks (with optional @start-end line anchors to pin a repeated block). Validates file read coverage and freshness before writing, reports any fuzzy tolerances it had to apply, then runs a tree-sitter syntax check (18+ languages) and points at the offending line with a snippet. The success message includes a compact diff of what changed.
MultiFileEdit	Validates and computes every requested edit in memory before writing any file, so a validation failure leaves the whole batch untouched. Commits then use atomic per-file renames; if a rare I/O failure occurs during that phase, already-written files are reported and are not rolled back. For a single file use FileWriteOrEdit.
UndoEdit	Reverts a file to its content before the last FileWriteOrEdit/MultiFileEdit this session (per-file, last ~10 edits kept in memory). Refused if the file changed on disk since your edit; a brand-new file's creation isn't undoable.
ContextSave	Dumps task description + file globs into a single text file with workspace context, active files, and git status/diff for clean handoff and task resumption.
ReadImage	Returns a native MCP image content block (not base64 as text), so multimodal models actually see the image. Confined to the workspace (like ReadFiles) and size-capped.
CodeMap	Tree-sitter code navigation, in one tool with two operations. outline: a symbol map (functions, types, methods, ...) - a file returns its definitions, a directory (or empty) a relevance-ranked, token-budgeted repo symbol map, in 11 languages. references: where a name is defined and used (called) across the repo, counting only real identifier occurrences (never inside strings/comments, unlike grep), definitions first. For plain-text/regex search and file discovery, just use rg/fd/grep via BashCommand.

Winx advertises MCP 2026-07-28. CodeMap publishes an outputSchema for its existing structuredContent, while text content remains available for older clients. MCP Tasks are optional on BashCommand and apply only to a foreground command; include an explicit thread_id and do not combine the protocol-level task object with is_background=true. Task results are retained for the negotiated, bounded TTL and may be fetched repeatedly until expiry.

On local stdio connections, a client that advertises MCP Roots can initialize Winx from its first usable local file:// root. Winx never changes an active workspace after a Roots update. Automatic Roots bootstrap is disabled on the shared HTTP service so one remote client cannot silently select another client's workspace.

Search/Replace editing

Standard block syntax:

<<<<<<< SEARCH
old content
=======
new content
>>>>>>> REPLACE

Things the matcher forgives so you don't have to babysit the model:

• atomic: ambiguous or missing matches abort without touching the file
• adjusts replacement indentation when the LLM gets the leading whitespace wrong
• strips ReadFiles line numbers if they leak into a SEARCH block
• normalizes the usual "smart quote" / em-dash / ellipsis substitutions
• uses neighboring blocks to disambiguate when the same snippet appears twice
• single-line substring edits work - you don't need the whole line in SEARCH
• retries once with \" unescaped when the model over-escapes quotes in SEARCH
• refuses edits that only matched after too much fuzzy fixup, and rejects blocks that match in too many places - so you re-read instead of corrupting the file
• anchor a block to a line number to pin one of several identical snippets - <<<<<<< SEARCH @42 (or a range @42-50); a stale anchor falls back to the normal search, so it never fails an otherwise-valid edit
• tells you on success which tolerances it had to apply (so you learn your SEARCH drifted), and on a miss how close the nearest match was, with ~ marking the lines that diverged

Install

The remote-first quickstart is at the top of this README. This section covers package installation and local stdio client recipes.

cargo install winx-code-agent

On Linux/macOS/WSL2 this installs winx-code-agent, winxd, and winx-guardian together in ~/.cargo/bin. Keep the three binaries together: the adapter auto-starts winxd, which starts one guardian per shell session. Every config snippet below assumes that directory is on $PATH; with a sterile client environment, use the absolute path returned by which winx-code-agent.

Needs Rust 1.88+, bash, and a real terminal. The durable daemon runtime is supported on Linux/macOS/WSL2. Native Windows uses the embedded runtime, so its shell sessions remain tied to the MCP server process; WSL2 is recommended. GitHub Release downloads for Unix are .tar.gz bundles containing all three sibling binaries, while the Windows asset remains a standalone embedded-runtime executable.

One-liner via the CLI (stdio is the default transport):

claude mcp add winx -- winx-code-agent

Or drop a .mcp.json in your project root:

{
  "mcpServers": {
    "winx": {
      "command": "winx-code-agent",
      "env": { "RUST_LOG": "winx_code_agent=info" }
    }
  }
}

Add to your config file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "winx": {
      "command": "winx-code-agent",
      "env": { "RUST_LOG": "winx_code_agent=info" }
    }
  }
}

Restart Claude Desktop after saving.

One-liner:

codex mcp add winx -- winx-code-agent

Or edit ~/.codex/config.toml:

[mcp_servers.winx]
command = "winx-code-agent"
env = { RUST_LOG = "winx_code_agent=info" }

Add to ~/.cursor/mcp.json (or .cursor/mcp.json for project-local):

{
  "mcpServers": {
    "winx": {
      "command": "winx-code-agent",
      "env": { "RUST_LOG": "winx_code_agent=info" }
    }
  }
}

Add to .vscode/mcp.json:

{
  "servers": {
    "winx": {
      "type": "stdio",
      "command": "winx-code-agent"
    }
  }
}

Add to your Zed settings (~/.config/zed/settings.json):

{
  "context_servers": {
    "winx": {
      "source": "custom",
      "command": "winx-code-agent",
      "args": [],
      "env": { "RUST_LOG": "winx_code_agent=info" }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "winx": {
      "command": "winx-code-agent",
      "env": { "RUST_LOG": "winx_code_agent=info" }
    }
  }
}

Add to opencode.json:

{
  "mcp": {
    "winx": {
      "type": "local",
      "command": ["winx-code-agent"],
      "enabled": true,
      "environment": { "RUST_LOG": "winx_code_agent=info" }
    }
  }
}

Add to ~/.gemini/settings.json:

{
  "mcpServers": {
    "winx": {
      "command": "winx-code-agent",
      "args": [],
      "env": { "RUST_LOG": "winx_code_agent=info" }
    }
  }
}

agy is Google's new Gemini-powered CLI (Go binary, usually at ~/.local/bin/agy). No mcp add subcommand yet - it reads MCP servers from JSON.

Edit ~/.gemini/config/mcp_config.json (also ~/.gemini/antigravity/mcp_config.json if you run the Antigravity IDE alongside):

{
  "mcpServers": {
    "winx": {
      "command": "winx-code-agent",
      "env": { "RUST_LOG": "winx_code_agent=info" }
    }
  }
}

If winx-code-agent is not on the agy process $PATH, swap command for the absolute path (~/.cargo/bin/winx-code-agent after cargo install winx-code-agent).

Add to your ~/.continue/config.yaml:

mcpServers:
  - name: winx
    command: winx-code-agent
    env:
      RUST_LOG: winx_code_agent=info

Add to ~/.kiro/settings/mcp.json:

{
  "mcpServers": {
    "winx": {
      "command": "winx-code-agent",
      "env": { "RUST_LOG": "winx_code_agent=info" }
    }
  }
}

Settings → MCP Servers → Add MCP Server:

{
  "winx": {
    "command": "winx-code-agent",
    "env": { "RUST_LOG": "winx_code_agent=info" }
  }
}

Add to your Roo Code MCP config:

{
  "mcpServers": {
    "winx": {
      "type": "stdio",
      "command": "winx-code-agent"
    }
  }
}

Any client that speaks stdio MCP works with this shape:

{
  "mcpServers": {
    "winx": {
      "command": "winx-code-agent",
      "args": [],
      "env": { "RUST_LOG": "winx_code_agent=info" }
    }
  }
}

If your client launches Winx with an empty $PATH, swap command for the absolute path ( ~/.cargo/bin/winx-code-agent).

For unreleased changes or a custom build:

git clone https://github.com/gabrielmaialva33/winx-code-agent.git
cd winx-code-agent
cargo install --path .

Or build and run the complete Unix daemon bundle without installing:

cargo build --release --locked --bins
./target/release/winx-code-agent

For a quick in-process development run that deliberately skips winxd and winx-guardian:

WINX_EMBEDDED=1 cargo run --release

Check it's wired up

List MCP tools in your client. You should see nine entries: Initialize, BashCommand, ReadFiles, FileWriteOrEdit, MultiFileEdit, UndoEdit, ContextSave, ReadImage, CodeMap. Start with Initialize unless your local client exposes MCP Roots and Winx bootstraps from them; Winx tracks workspace + mode per thread.

Durable session lifecycle (Unix)

The daemon runtime caps live guardians at 32 by default and uses tiered idle retention: a shell that has never run a command expires after 30 minutes, while a used shell expires after 24 hours. A foreground command or live background command is never removed. New guardians report their own creation, activity, and command clocks; the control-plane JSON beside each socket is only a permission-protected cache. For protocol-1.2 guardians, Winx uses real request metadata and the socket birth time instead of treating a recreated tmpfs metadata file as fresh activity.

# Inspect and attach
winx-code-agent list
winx-code-agent attach <thread_id> --follow

# Explicit cleanup
winx-code-agent kill <thread_id>
winx-code-agent kill --all

# Apply the tiered defaults (30 min never-used / 24 h used)
winx-code-agent prune

# Override both tiers; zero removes every idle session but preserves active commands
winx-code-agent prune --idle-seconds 0

# Reload winxd after changing lifecycle environment variables; guardians survive
winx-code-agent restart-daemon

# Print a redacted configuration/runtime report
winx-code-agent doctor

The quota and TTL are enforced by winxd, not just by one MCP adapter, so reconnecting clients and multiple adapters share the same resource boundary. Under quota pressure, Winx first reclaims the oldest inactive guardian that has never run a command; used or active shells are never sacrificed to admit a new session. If no disposable guardian exists, the error points to the effective force-prune command: winx-code-agent prune --idle-seconds 0.

A newly installed adapter upgrades an older control plane automatically when it advertises safe planned restarts; the per-session guardians and their PTYs stay alive throughout. Protocol 1.3 guardians are attach-or-create: repeating a first call for the same key preserves the PTY, cwd, output journal, and running command.

Streamable HTTP deployment

Streamable HTTP is Winx's primary interface for ChatGPT, hosted agents, remote automation, and any MCP client that cannot launch a local stdio process. The endpoint is always /mcp; the default listener is 127.0.0.1:8000.

Remote first calls default to --session-affinity workspace: the internal key is (principal, canonical workspace), so reconnections and harmless variations such as release_02333 versus release_0_2_333 resolve to one guardian. Parallel conversations from the same principal in the same repository therefore share one shell. Deployments that require separate shells may opt into --session-affinity thread, but then the client owns stable thread IDs and cleanup.

[!TIP] The full guide covers request headers, multi-principal configuration, private tunnels, operational limits, status codes, durable sessions, troubleshooting, and the exact security boundary: docs/streamable-http.md.

Deployment profiles

Profile	Credential model	Recommended exposure
Personal remote agent	One chmod-600 --token-file	Loopback + private tunnel or VPN
Several clients or automations	--principal-config with one token per client	Loopback + authenticated HTTPS edge
ChatGPT / OpenAI products	One dedicated principal per app	Secure MCP Tunnel or a reviewed public HTTPS proxy
Local IDE or CLI	No HTTP server; use stdio	Local process only

Multi-principal configuration

# ~/.config/winx-principals.toml
[[principals]]
name = "chatgpt"
token_file = "/home/alice/.config/winx-chatgpt-token"

[[principals]]
name = "automation"
token_env = "WINX_AUTOMATION_TOKEN"

chmod 600 ~/.config/winx-principals.toml ~/.config/winx-chatgpt-token
winx-code-agent serve --http \
  --principal-config ~/.config/winx-principals.toml

Each authenticated principal receives its own internal namespace. The same external thread_id can therefore be reused by different clients without sharing a workspace, shell, guardian, or MCP Task. Internal prefixes are translated back out of normal results and errors before the response reaches the client.

ChatGPT and OpenAI products

ChatGPT connects to remote MCP endpoints rather than directly launching a server on your machine. For private or local Winx deployments, OpenAI documents the Secure MCP Tunnel as an outbound-only path that avoids opening inbound firewall ports. Developer Mode availability and workspace controls evolve, so use OpenAI's current Developer Mode guide for the latest UI and plan requirements.

HTTP defaults

Control	Default
Bind address	127.0.0.1:8000; non-loopback requires --allow-non-loopback
Authentication	Authorization: Bearer <token>
Minimum token length	32 bytes, unless --allow-weak-token is explicitly set
Request body	64 MiB maximum
Request timeout	120 seconds
Concurrent requests	32 globally
Rate limit	120 requests/minute per source IP
Invalid authentication delay	100 ms
Query token	Disabled; requires --allow-query-token
Session affinity	workspace; thread is the explicit isolation opt-out
Never-used guardian TTL	1,800 seconds (30 minutes)
Used guardian TTL	86,400 seconds (24 hours)

Connector metadata

• Name: Winx
• Title: Winx High-Performance MCP
• Description:

Remote-first Rust MCP runtime that gives agents durable, authenticated access to a real PTY, guarded file editing, token-budgeted reads, image input, and tree-sitter code navigation. Streamable HTTP supports multi-principal session and Task isolation; stdio remains available for local clients.

The server advertises its icon in the initialize handshake (serverInfo.icons, MCP 2026-07-28). Source art lives in .github/assets/icon.png.

[!WARNING] A valid Winx principal is equivalent to shell and file access as the operating-system user. wcgw mode is intentionally powerful and BashCommand is not workspace-confined. Keep HTTP on loopback, prefer private connectivity, use architect or constrained code_writer sessions where possible, rotate leaked tokens, and stop the endpoint when it is no longer needed.

Environment variables

All optional - Winx works out of the box without any of these. Boolean variables accept the same case-insensitive values: 1/true/yes/on and 0/false/no/off.

Variable	Effect
RUST_LOG	Log verbosity, e.g. winx_code_agent=info. At info you get the per-call audit trail (tool name, arg summary, duration, ok/error).
WINX_HTTP_TOKEN	Single-principal HTTP bearer token used when --token, --token-file, and --principal-config are absent. Prefer a token file for long-lived deployments; see the Streamable HTTP guide.
WINX_RUNTIME	Runtime selection on Unix: daemon (default) or embedded. Native Windows is embedded-only.
WINX_EMBEDDED	Truthy value (1, true, yes, on) forcing the in-process runtime; useful as a fail-safe kill switch.
WINX_SOCKET	Override the Unix socket used to reach winxd.
WINXD_BIN / WINX_GUARDIAN_BIN	Override daemon/guardian executable discovery. Normally unnecessary when the three release binaries remain together.
WINX_MAX_GUARDIANS	Maximum live daemon-owned sessions across all adapters. Defaults to 32; accepted range is 1..=4096. Read when winxd starts; use restart-daemon after changing it.
WINX_SESSION_IDLE_TTL_SECS	Idle lifetime for sessions that have run a command. Defaults to 86400 (24 hours); 0 disables this tier. Active foreground/background commands are preserved. Read when winxd starts.
WINX_UNUSED_SESSION_IDLE_TTL_SECS	Idle lifetime for guardians that have never run a command. Defaults to 1800 (30 minutes); 0 disables this tier. Under hard quota pressure, the oldest inactive never-used guardian may still be reclaimed.
WINX_GUARDIAN_SWEEP_INTERVAL_SECS	Interval between automatic guardian sweeps. Defaults to 60 seconds; accepted range is 1..=86400. Read when winxd starts.
WINX_NO_COMPRESS	Set to 1 to disable output compression and see raw, uncollapsed shell output (the [winx: ×N] collapsing is on by default).
WINX_NO_REDACT	Set to 1 to disable secret redaction. By default winx scrubs high-confidence credentials (provider API keys, JWTs, PEM private keys, user:pass@ URLs) from all tool output and saved memory, replacing each with [REDACTED:<rule>]. Turn this off only when you knowingly need a raw value.
WINX_ALLOW_PATHS	:-separated absolute paths the file tools (ReadFiles, FileWriteOrEdit, MultiFileEdit, ReadImage, UndoEdit, CodeMap) may reach outside the workspace (e.g. WINX_ALLOW_PATHS=/tmp). Empty by default: everything stays workspace-confined. Read once at startup, so the policy is set by whoever launches the server and cannot be widened mid-session by a tool argument or a shell command. WINX_ALLOW_PATHS=/ turns containment off entirely (every absolute path is under /) - the explicit way to run unconfined. Note BashCommand was never path-confined; this only governs the file tools.
WINX_SANDBOX	Set to 1 to enable an opt-in Landlock filesystem sandbox (Linux 5.13+, EXPERIMENTAL). Confines winx and its shell to write only the workspace (the cwd at startup) plus /tmp, and makes the home directory unreadable, so a manipulated agent can't read ~/.ssh/~/.aws or modify files outside the project. Coarse and best-effort: a command needing a path outside the allowlist fails. Degrades to a warning (unsandboxed) on older kernels.
WINX_SANDBOX_RO_PATHS / WINX_SANDBOX_RW_PATHS	:-separated absolute paths to additionally allow read-only / read-write under WINX_SANDBOX (e.g. WINX_SANDBOX_RO_PATHS=$HOME/.cargo:$HOME/.rustup so cargo still works).
WINX_TURN_RECOGNIZER_CONFIG	JSON {"busy":[…],"awaiting_input":[…],"awaiting_approval":[…]} of marker strings/regexes. With recognizer:"configurable", lets wait_for_turn drive an arbitrary TUI without bespoke code.
WINX_CODING_TOKEN_BUDGET / WINX_NONCODING_TOKEN_BUDGET	Override the per-file token budget for ReadFiles (and saved memory) - raise it for large-context models. Defaults: 24000 / 8000.
WINX_KEEP_TAIL_PIPE	Set to 1 to keep a trailing | tail … instead of stripping it. Winx truncates output server-side, so by default it drops a redundant trailing tail (wcgw parity).
WINX_USE_SCREEN / WINX_ATTACH_TERMINAL	Run the shell inside screen/tmux so you can attach to the live session. Set to screen, tmux, or any truthy value; Winx prints an attach hint on Initialize.
WINX_OPEN_CONTEXT	Set to 1 to open the saved context file in your default app after ContextSave.
WINX_SHELL	Set to zsh to run the session under zsh instead of bash (opt-in; bash stays the default). Falls back to bash if zsh isn't on PATH or the mode is restricted.
WINX_SERVER_INSTRUCTIONS	Extra operator instructions appended to every Initialize response (e.g. house rules for the agent).

Verifying releases

Each GitHub release contains the platform artifact, its .sha256 file, an aggregate SHA256SUMS, and a CycloneDX JSON SBOM. The workflow also publishes GitHub artifact attestations for the binaries and the SBOM relationship.

sha256sum --check winx-linux-amd64.tar.gz.sha256
sha256sum --check SHA256SUMS

Hacking on it

cargo fmt --all -- --check
cargo check --all-features --locked
cargo clippy --all-targets --all-features --locked -- -D warnings
cargo test --all-features --locked
cargo +1.88.0 check --all-features --locked
cargo package --locked
cargo bench --bench performance --locked --no-run
cargo deny --all-features check
cargo audit --deny warnings
cargo +nightly fuzz build

CI runs these contracts in dedicated jobs, including the ignored real-PTY/TUI tests on Linux. If you touch PTY, terminal, BashCommand, file editing, authentication, or persistence, run the focused regression suite before the full matrix.

Robustness is also fuzzed and model-checked:

• proptest feeds arbitrary/adversarial bytes into the live terminal emulator, the ANSI stripper, and the exit-code parser, asserting they never panic and stay within the viewport. (This is how we found - and worked around - a vt100 underflow on tiny grids and a reflow panic on column shrink that would otherwise crash the panic = "abort" release.)

• loom exhaustively model-checks the session pin counter (the lock-free guard that keeps an in-flight session from being LRU-evicted) across every thread interleaving. It's behind a feature so it doesn't perturb the normal build:

  cargo test --features loom --lib loom_
  

A note on security

Winx supports local stdio and remote Streamable HTTP. Anything connected to either transport can read files, edit files, and run shell commands with the capability granted by the selected mode - the same blast radius as giving the client a terminal. HTTP extends that reach beyond the local process boundary; read the Streamable HTTP deployment guide and SECURITY.md before exposing it.

Two things are on by default to reduce the blast radius: secret redaction scrubs high-confidence credentials from all tool output and saved memory (WINX_NO_REDACT=1 to disable), and the PTY shell's whole process group is killed on teardown so background jobs it spawned don't leak.

If you want a tighter leash:

• architect mode disables writes and most commands;
• code_writer mode lets you allowlist commands and write globs;
• WINX_SANDBOX=1 enables an opt-in Landlock filesystem sandbox (Linux): writes are confined to the workspace plus /tmp, and the home directory is unreadable, so a manipulated agent can't read ~/.ssh/~/.aws or modify files outside the project.

SECURITY.md has the disclosure process and threat model.

License

MIT – Gabriel Maia (@gabrielmaialva33)