v1.0.2 RELEASED · 2026-05-05 Daemon · Swarm · Self-dev · Voice · Importer · Mermaid. Sub-50ms warm round-trip. See what's new →
v1.0.2 — The Open AI Agent OS

The AI that
actually does things.

Local-first AI agent OS for your machine. Daemon mode in sub-50ms, swarm runner across isolated git worktrees, sandboxed self-dev that only ships if tests pass, voice dictation, mermaid in the dashboard, and a one-shot importer that pulls your context out of Claude Code, Codex, or OpenCode. Tiered sandbox, signed plugins, multi-channel reach, Memory v2 — all built in. One product. One price. Yours forever.

⚡ Phantom v1.0.2 · Local AI Agent OS
Works with any OpenAI-compatible AI provider
Groq
NVIDIA NIM
Anthropic
Together AI
Ollama (local)
DeepSeek
Fireworks AI
Mistral
LM Studio
OpenAI
Groq
NVIDIA NIM
Anthropic
Together AI
Ollama (local)
DeepSeek
Fireworks AI
Mistral
LM Studio
OpenAI
// v1.0.2 · just released · 2026-05-05

Ten new powers.
One unified version.

Phantom v1.1.35 ships in two tiers. Free covers chat, plugins, memory, MCP, bench, doctor — all forever, no card needed. Pro (₹999 lifetime) adds daemon mode, swarm runner, sandboxed self-dev, and voice dictation. Pro features are unlocked free for the first 14 days so you can try them. Existing licence holders just /update; pre-gate users are grandfathered. Every future patch free, on both tiers.

ONE-LINE INSTALL · Single command · One ₹999 lifetime licence
LINUX / MACOS
curl -fsSL https://phantom.aravindlabs.tech/install.sh | bash
WINDOWS POWERSHELL
irm https://phantom.aravindlabs.tech/install.ps1 | iex
Direct download: phantomcli-source.zip  ·  Manifest: version.json  ·  Existing users — just run /update.

Daemon Mode NEW

phantom serve opens a unix-socket daemon; phantom connect attaches in sub-50 ms. Closes the cold-start gap against Rust harnesses without a rewrite. macOS connect-before-accept race fixed with a warm-up retry ping.

Swarm Runner NEW

phantom swarm "<goal>" --agents N fans N subagents into isolated git worktrees, runs them in parallel, collects diffs, and flags file-level conflicts before merge. Try the same task three ways and pick the winner.

Sandboxed Self-Dev NEW

phantom self-dev "<change>" applies an edit in a worktree, runs your full test suite there, and only swaps onto your branch (with --swap) if everything stays green. Iterate without ever breaking main.

Voice MVP NEW

phantom dictate records via sox/arecord/parecord and transcribes through Whisper. Stub backend ships for offline tests so CI doesn't need a microphone. On top of the existing voice loop with VAD-driven STT/TTS and barge-in cancellation.

Cross-Harness Importer NEW

phantom memory import {claude-code,codex,opencode} pulls transcripts from other agents straight into Phantom's episodic memory — switch tools without losing context. Pair with phantom mcp import which slurps ~/.claude/mcp.json and ~/.codex/mcp.json in one command. No more re-pasting server configs.

Reproducible Benchmarks NEW

phantom bench prints cold-start time, daemon round-trip, RSS, turn-latency p50/p95, and scaling slope as JSON. Methodology baked in — anyone can verify the sub-50 ms claim on their own machine.

Custom OpenAI-Compatible Providers NEW

phantom config provider custom <name> --base-url --model --key-env registers vLLM, Ollama, LM Studio, or any OpenAI-shaped endpoint in one shot. No code edits, no JSON hand-editing.

Mermaid in Dashboard NEW

Fenced ```mermaid blocks render live in the web dashboard via the official renderer with securityLevel: 'strict' and a MutationObserver for streamed inserts. Architecture diagrams arrive drawn, not as ASCII.

Three New First-Party Plugins NEW

github-pr — gh CLI inspector for any PR. web-screenshot — Playwright PNG capture of any URL. code-review — pure-Python static lints over a unified diff. Demonstrates the Ed25519-signed plugin SDK end-to-end. Existing 5 (clock, weather, gh-search, code-search, todo) carry forward — eight first-party plugins total.

The complete platform — all built in.

Tiered sandbox (bubblewrap → firejail → unshare → docker on POSIX, passthrough on Windows v1.0), Ed25519-signed plugin SDK, multi-channel adapters (WebChat / Telegram / Discord / Slack / Matrix), MCP both-ways (client + server), ACP child-agent runtime with topological waves, Skills (SKILL.md bundles), Memory v2 (SQLite + FTS5 + TF-IDF reranker), realtime voice with barge-in, typed Canvas UI, PWA + service worker, i18n in 5 languages, KeyPool round-robin rotation, OTel-shaped metrics. Release date: 2026-05-05. ₹999 lifetime — every v1.0.2 capability included, every future patch included.

Existing users — your licence and install path are preserved. Run /update in your REPL. Both phantom (canonical) and python run.py (alternate entry point) keep working.

// capabilities

Everything you need.
Nothing you don't.

Designed to execute tasks on your local machine with real OS access, permanent memory, and remote control from your phone.

Dual-Engine AI Architecture

A heavy Main Engine handles reasoning, coding, and execution. A fast Router Engine classifies your prompt and shapeshifts into the right specialist — File Organizer, DevOps Agent, Code Writer, or Security Auditor. Works with any OpenAI-compatible provider.

God Mode Execution

Real bash commands on your machine. 48 catastrophic patterns permanently blocked. Trust levels 1–4. Level 4 requires your PHC license key to unlock — and auto-downgrades to Trust 3 after 30 minutes idle.

Telegram Remote Control

Full two-way chat with PhantomCLI from your phone. All /commands work. Separate trust level from local CLI. Owner-only security gate.

Media API Integrations

Image generation (FAL.ai, DALL-E, Stability, Replicate), voice TTS (ElevenLabs, OpenAI, PlayHT), speech-to-text (Deepgram). Configure once, use via natural language.

3-Device License

One purchase activates up to 3 machines. Hardware fingerprinting + server-side enforcement. Manage devices via python run.py setup.

JARVIS Sci-Fi TUI

Boot sequence, HUD panels, Claude Code-style thinking spinner. Local web dashboard at localhost:8080. Nothing hosted externally — your data stays on your machine.

Live Task Progress

Every tool call — shell, file write, search, edit — is shown as a live checklist (◻ → ◼ → ✔ / ✖) in both the terminal and the web dashboard. For multi-step jobs the model plans upfront, so you see exactly where it is.

ML & Data Pipelines

Hand it a dataset — it auto-installs pandas, scikit-learn, xgboost, plotly, transformers, whatever fits the task. Writes modular Python, trains the model, serves an interactive FastAPI / Flask / Streamlit dashboard and prints the URL.

9-Event Hook Lifecycle

PreToolUse, PostToolUse, UserPromptSubmit, Stop, SubagentStop, SessionStart/End, PreCompact, Notification. Shell hooks (stdin JSON) + programmatic Python hooks via @hook decorators. Non-zero exit blocks for binding events; fail-open on timeout.

Pattern Permissions + Audit Chain

Scoped allow/deny/ask: bash:git:*, write:~/projects/**, deny:bash:rm:*. Every decision hash-chained into ~/.phantom/audit.jsonl. Tamper-detectable with /audit verify.

CLAUDE.md Hierarchy — with Live Reload

Auto-loads CONTEXT.md from three scopes (user, project-root, local dir) into the system prompt on session start. Poll-based watcher picks up edits live — no restart needed.

Multi-Tier Model Routing

Classifier picks cheap tier (tool-arg turns), mid tier (default), or expensive tier (reasoning cues) per turn. Cuts token cost 40–60% vs single-model. Per-model price sheet + daily spend alerts via the Notification hook.

VS Code Extension

Dedicated activity bar with 4 tree views (Sessions, Memories, Hooks, Tools). 5 code actions on any selection: explain, refactor, fix, add tests, document. Quick Pick palette, rich status bar with live cost tile, workspace context injection (active file + open files + diagnostics), transcript export to Markdown, inline diff preview. Stdio bridge to the CLI.

MCP Resources + Reconnect

Model Context Protocol client with resources/list, resources/read, subscribe/unsubscribe, and auto-reconnect with exponential backoff. Every MCP tool call surfaces in the model's structured tool list.

Dual Streaming Parsers

Native Anthropic SSE (message_start / content_block_delta / message_stop) AND OpenAI-compatible chunks. UTF-8 chunk-boundary safety, partial-JSON repair for tool args truncated mid-stream. 60+ combined tests.

OpenTelemetry Observability

Every model call + tool dispatch + hook fire emits a phantom.* OTel span with latency, tokens, ok/error. Point OTEL_EXPORTER_OTLP_ENDPOINT at Honeycomb / Datadog / Jaeger. In-memory exporter for local debugging.

Self-Heal After Launch

When you ask Phantom to build and run an app, it HTTP-GETs the URL after launch, detects 5xx / tracebacks in the body, reads the log, auto-patches the source, relaunches — before claiming "live". Tested against real Flask apps.

Parallel Subagents + Scratchpad

Multi-agent orchestrator runs dependency-ordered waves in parallel. SQLite-backed scratchpad lets upstream agents publish partial results downstream agents read mid-run — faster than re-running prompts. 6 built-in agent types with tool allowlists + worktree isolation.

11 Slash Commands + User-Defined

/help /clear /model /memory /perm /hook /session /compact /cost /exit. Drop a ~/.phantom/commands/mycmd.md for your own templates with frontmatter description.

4-Layer Settings Hierarchy

System → user → project-shared → project-local, with locked_keys for enterprise. 128K-token context compaction with PreCompact hook + LLM-backed summariser. Session save/load with atomic writes.

Iterative Web Research

/web now does Claude-Code-style two-round research: round 1 scrapes the top 5 pages, the router model inspects the gaps and proposes 2 specific follow-up queries, round 2 scrapes 2 more pages each — ~9 pages total at 6,000 chars each. Output is clean narrative (no Step 1/2/3 spam, no inline citation noise). Run /sources after to see the URLs with first-line previews. ~30–60s wall time, dramatically deeper answers.

Refinement-Aware Project Router

Follow-ups like "ui is not good" or "also add login" stay in the active project instead of spawning a new project_xxxxxxxx. Two-tier router detects refinement cues + active project and continues silently. Every refinement appended to phantom_summary.md as a run-history entry. Hardened multi-agent fallback: if the planner returns malformed JSON, a 4-agent default skeleton (Fetcher, Backend, Frontend, Runner) always produces a working build.

Clean Self-Update

/update auto-exits the REPL on a successful upgrade so Python's sys.modules cache can't silently keep running stale code. Failed updates and "already-latest" cases stay in the REPL so you can retry. Backed by 4 dedicated tests + the full 775-Python-test suite (903 with TS + VS Code).

// quickstart

From zero to running
in 60 seconds.

1
Buy Once
Pay ₹999. License key + 3 personalised install commands sent to your email instantly.
₹999 · One-time
2
Install
One command on Linux, macOS, or Windows PowerShell. All dependencies auto-installed.
curl …install.sh?key=PHC-XXXX | bash
3
Launch
Run setup, open localhost:8080. All computation stays on your machine — zero cloud dependency.
python run.py dashboard
// comparison

Built different.
By design.

How PhantomCLI stacks up against other local AI agents.

Scroll table to compare →

Feature Phantom v1.0.2 Claude Code OpenClaw AutoGPT AgentZero
Any OpenAI-compatible model
Local OS bash execution
9-event hook lifecycle
Pattern permissions (bash:git:*, write:~/**)
Hash-chained audit log
CLAUDE.md hierarchy with live reload
Multi-tier model routing (cheap/mid/expensive)
VS Code extension with activity bar + code actions
MCP resources + subscribe + reconnect
Anthropic SSE + OpenAI SSE streaming  Anthropic only
Programmatic Python hooks (@hook decorator)  shell only
Parallel multi-agent with shared scratchpad  sequential only
Self-heal after launching built apps
OpenTelemetry spans + metrics
Telegram two-way bot
Persistent memory — episodic log + FTS5 RAG
Image / Video / Voice APIs
Permanent dangerous-cmd blocklist
Live task-progress checklist
Auto ML pipelines + dashboards
One-time payment, lifetime  Anthropic sub
// early feedback

What beta testers say.

★★★★★

"Getting local OS execution working was shockingly simple. It organised my entire Downloads folder in one sentence."

AR
Arjun R.Backend Engineer · Bangalore
★★★★★

"Telegram integration is insane. I literally SSH into my VPS by texting my bot while commuting. Set it up in 10 minutes."

SK
Suresh K.DevOps Engineer · Chennai
★★★★★

"Replaced 8 Python automation scripts with natural language. The God Mode terminator animation when you hit Level 4 is 🔥"

MR
Meera R.Full-Stack Developer · Mumbai
// pricing

One price. Forever yours.

No monthly fees. No hidden charges. Buy once and own PhantomCLI for life.

₹999
One-time payment · Lifetime license · No subscription

Secured by Razorpay License in 60 seconds 3-device activation Free lifetime updates No cloud — runs locally
Already purchased?
// faq

Frequently asked questions.

No. Everything runs locally on your machine. Conversations, files, and command history never leave your computer. The only external calls are to AI provider APIs you configure with your own keys, and license validation at activation time.
Any model that follows the OpenAI API format — just provide a Base URL, API Key, and Model name. This covers Groq, NVIDIA NIM, Together AI, Fireworks, DeepSeek, Mistral, Anthropic, and local runtimes like Ollama and LM Studio. If it has an OpenAI-compatible endpoint, PhantomCLI can use it.
No — it runs at localhost:8080 on your own machine. Aravind Labs servers are only involved in purchase and license key validation.
Yes. Open PowerShell and run the one-liner from your purchase email: irm "https://phantom.aravindlabs.tech/phantomcli/install.ps1?key=PHC-XXXX" | iex
New in v1.0.2. Run phantom serve in one terminal — it opens a unix-socket daemon. Run phantom connect in another (or any IDE/script) and you get sub-50 ms warm round-trip instead of paying Python startup every time. Tiered sandbox (Trust 1–4) and 48-pattern dangerous-command blocklist still apply. Trust 4 ("God Mode") still requires your licence key and auto-downgrades to Trust 3 after 30 min idle.
Yes. Run phantom memory import claude-code (or codex, opencode) and your transcripts move into Phantom's episodic memory. phantom mcp import grabs ~/.claude/mcp.json and ~/.codex/mcp.json in one shot. No re-pasting server configs.
The 4th activation is rejected. Deactivate a slot via python run.py setup → option 9. Need help? Email support@aravindlabs.tech.
No subscription, no recurring charge. ₹999 is a single one-time payment that unlocks Pro features (daemon mode, swarm, voice, self-dev) on up to 3 devices, with every future update included forever. The Free tier (chat + plugins + memory + MCP + bench + doctor) stays free for everyone, and Pro features are unlocked free for the first 14 days so you can try them before deciding.
Basic comfort with a terminal is helpful but not required. The setup wizard walks you through every step. Once running, you just type in plain English — "organise my Downloads folder", "check disk usage", "push my git changes" — and PhantomCLI handles the rest. The web dashboard at localhost:8080 needs no command-line knowledge at all.
ChatGPT tells you what command to run. PhantomCLI actually runs it. It has direct access to your filesystem, can execute bash scripts, browse the web for live data, control your machine via Telegram, and remember context across sessions. It's the difference between an advisor and an employee.
Local-first · No cloud lock-in

Your machine is waiting.

v1.0.2 ships today. Daemon, swarm, self-dev, voice, importer — all included. ₹999 once, yours forever, every future patch free.

Get Phantom v1.0.2 Now