{"slug": "quanta-ai-code-editor", "title": "Quanta.Ai.Code.Editor", "summary": "Quanta, a local-first AI code editor built on VS Code OSS with a Rust backend, has been released, offering agentic coding powered primarily by local LLMs via Ollama, with optional cloud backends. The editor includes 30+ built-in tools, a ReAct agent loop, three agent modes, sub-agent spawning, persistent todo lists, shadow-git checkpoints, full LSP integration, and MCP support, ensuring code never leaves the machine.", "body_md": "Quanta is a **local-first AI code editor** built on VS Code OSS, powered by a high-performance Rust backend. It gives you a complete agentic coding experience — reading files, writing code, running terminals, applying LSP fixes, and managing git — all driven by local LLMs through [Ollama](https://ollama.ai). Cloud providers (OpenAI, Anthropic) are supported as optional backends, but Ollama is the primary engine. Your code never has to leave your machine.\n\nUnlike cloud-first AI editors, Quanta is designed around local inference. The agent loop, tool execution, LSP integration, checkpoint system, and inline completions all happen locally through a Rust backend that communicates with the editor via JSON-RPC over TCP.\n\n[Key Features](#key-features)[Feature Comparison](#feature-comparison)[Architecture](#architecture)[Quick Start](#quick-start)[Installation](#installation)[Agent Tools](#agent-tools)[Agent Modes](#agent-modes)[LSP & Diagnostics](#lsp--diagnostics)[Checkpoint System](#checkpoint-system)[Edit History & Undo/Redo](#edit-history--undoredo)[MCP Integration](#mcp-integration)[Model Management](#model-management)[HuggingFace Integration](#huggingface-integration)[Engineering Skills](#engineering-skills)[Voice & TTS](#voice--tts)[Session Management](#session-management)[Plan Mode](#plan-mode)[Configuration](#configuration)[License](#license)\n\n**30+ built-in tools**— read/write/edit files, unified diffs, terminal, grep, glob, git operations, LSP actions, and more** ReAct agent loop**— Think, Act, Observe, Feedback pattern with anti-loop guards and automatic retries** 3 agent modes**— Code (full capability), Ask (read-only), Plan (read-only + plan writing)** Sub-agent spawning**— Delegate scoped tasks to parallel sub-agents with up to 3 levels of nesting** Persistent todo lists**— Track multi-step work across conversation turns\n\n**Ollama integration**— Auto-detects and lists all local models with metadata** Thinking/reasoning support**— Configurable think levels (Low/Medium/High) for reasoning models** Inline code completion**— FIM completions with LRU cache, debouncing, and in-flight cancellation** Local-first by design**— Ollama is the primary backend; cloud providers (OpenAI, Anthropic) are optional. Your code never has to leave your machine.\n\n**Shadow-git checkpoints**— Automatic workspace snapshots before every agent write action** Edit review system**— Accept/reject individual edits with diff previews** Stale-file detection**— Prevents edits to files that changed since last read** Terminal safety guards**— Blocks destructive commands (format, shutdown, force-delete)** Atomic writes**— All file operations use temp-file-and-rename for crash safety\n\n**Full LSP integration**— Diagnostics, go-to-definition, find references, code actions, rename symbol** 20+ engineering skills**— Built-in guidance for TDD, code review, security review, debugging, and more** MCP support**— One-click enable for GitHub, Jina AI, Brave Search, Postgres, Puppeteer, and more** HuggingFace model browser**— Search, download, and install GGUF models directly from the editor** Per-model configuration**— Override temperature, think level, edit format, tool call mode, and more per model** Voice support**— Speech-to-text via Whisper, text-to-speech via Piper\n\nNote:Competitor data is based on publicly available documentation as of 2025. Features change frequently — verify with each tool's official docs before relying on this table for decisions. A dash (—) means we could not verify the feature's presence or absence and chose not to guess.\n\n| Feature | Quanta | Cursor | Claude Code | Zed AI | Aider | Cline |\n|---|---|---|---|---|---|---|\nLocal LLM (Ollama) |\nYes | Limited ¹ | Yes ² | Yes | Yes | Yes |\nOllama as primary backend |\nYes | No | No | No | No | No |\nBuilt on VS Code |\nYes | Yes | No (CLI) | No (Zed) | No (CLI) | Yes (extension) |\nRust backend |\nYes | No | No | Yes | No | No |\nPersistent shadow-git checkpoints |\nYes | No ³ | No | No | No | Yes |\nEdit review (accept/reject) |\nYes | Yes | No | No | No | Yes |\nLSP diagnostics to model |\nYes | Yes | No | Yes | No | Yes |\nLSP code actions to model |\nYes | — | No | — | No | — |\nLSP rename symbol to model |\nYes | — | No | — | No | — |\nInline completion (local) |\nYes | Yes | No | Yes | No | No |\nSub-agent spawning |\nYes | No ⁴ | Yes | No | No | No |\nPlan mode |\nYes | Yes | No | No | No | Yes |\nMCP support |\nYes | Yes | Yes | No | No | Yes |\nHuggingFace model browser |\nYes | No | No | No | No | No |\nPer-model config overrides |\nYes | No | No | Partial | No | No |\nPer-task model routing |\nYes | Yes | Yes | Yes | No | No |\nEngineering skills |\nYes | No | No | No | No | No |\nVoice (STT + TTS) |\nYes | No | No | No | No | No |\nSession export (MD/JSON/PDF) |\nYes | No | No | No | No | No |\nConfigurable thinking levels |\nYes | No | No | No | No | No |\nTool call modes (parallel/sequential) |\nYes | No | No | No | No | No |\nTree-sitter fallback diagnostics |\nYes | No | No | No | No | No |\nCustom skills (project + global) |\nYes | No | No | No | No | No |\nTodo list tracking |\nYes | No | Yes | No | No | Yes |\n\n**Footnotes:**\n\n**Cursor**— Supports Ollama via OpenAI-compatible endpoint for chat and tab completion, but agent modes do not work with local LLMs as of May 2025 (community feature request open).**Claude Code**— Supports local Ollama models via Anthropic-compatible API endpoint (Ollama 0.14+). Cloud (Anthropic) is the default backend.**Cursor**— Has session-local checkpoints that do not persist across IDE restarts and do not use a shadow git repository. They capture file changes only, not terminal side effects.**Cursor**— Has parallel agents via git worktrees (Agents Window) and`/best-of-n`\n\nmulti-model runs, but does not support spawning sub-agents from within an ongoing conversation.\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│                     Quanta AI Editor                        │\n│  ┌───────────────────────────────────────────────────────┐  │\n│  │              VS Code OSS (Electron Frontend)          │  │\n│  │  ┌───────────────┐  ┌─────────────┐  ┌──────────────┐ │  │\n│  │  │  Chat Webview │  │   Editor    │  │  Inline Comp │ │  │\n│  │  │  (TypeScript) │  │  (Monaco)   │  │  (TypeScript)│ │  │\n│  │  └──────┬────────┘  └──────┬──────┘  └──────┬───────┘ │  │\n│  │         │                  │                │         │  │\n│  │  ┌──────┴──────────────────┴────────────────┴───────┐ │  │\n│  │  │           Quanta Extension (TypeScript)          │ │  │\n│  │  │     RPC Client · Diagnostics · LSP Bridge        │ │  │\n│  │  └──────────────────────┬───────────────────────────┘ │  │\n│  └─────────────────────────┼─────────────────────────────┘  │\n│                            │ JSON-RPC 2.0 over TCP          │\n│  ┌─────────────────────────┴─────────────────────────────┐  │\n│  │              Quanta Backend (Rust)                    │  │\n│  │  ┌─────────────┐  ┌──────────────┐  ┌──────────────────┐ │  \n│  │  │ Agent Loop  │  │ Tool Registry│  │  Session Manager │ │ \n│  │  │ (ReAct)     │  │ (30+ tools)  │  │  (persistence)   │ │ \n│  │  └──────┬──────┘  └──────────────┘  └──────────────────┘ │ \n│  │  ┌──────┴──────────────────────────────────────────────┐ │ \n│  │  │  Checkpoint Service · MCP · LSP Reverse RPC         │ │ \n│  │  └─────────────────────────────────────────────────────┘ │ \n│  │  ┌─────────────┐  ┌─────────────┐  ┌──────────────┐   │  │\n│  │  │   Ollama    │  │  OpenAI API │  │ Anthropic API│   │  │\n│  │  │ (localhost) │  │  (optional) │  │  (optional)  │   │  │\n│  │  └─────────────┘  └─────────────┘  └──────────────┘   │  │\n│  └───────────────────────────────────────────────────────┘  │\n└─────────────────────────────────────────────────────────────┘\n```\n\n**Key design principles:**\n\n- The extension is a thin UI layer — all agent logic lives in the Rust backend\n- Communication via newline-delimited JSON-RPC 2.0 over TCP (localhost only)\n- The backend manages tool execution, LSP reverse-RPC, checkpoints, sessions, and MCP\n- Cloud providers (OpenAI, Anthropic) are optional — Ollama is the primary inference engine\n\n-\n— Install and start the Ollama service[Ollama](https://ollama.ai)\n\n```\n# Install a model (example)\nollama pull qwen2.5-coder:7b\n```\n\n-\n**Git**— Required for the checkpoint system\n\n**Download** the latest release from the[Releases](/ContegoCode/Quanta-Code-Editor/releases)page**Extract** the archive and run`Quanta.exe`\n\n**Open a project** folder (File > Open Folder)**Open the chat panel**— Click the Quanta icon in the activity bar** Select a model**— Click the model name in the chat header to pick from your Ollama models** Start coding**— Ask Quanta to build features, fix bugs, refactor code, or explain your codebase\n\nTip:Use`@`\n\nin the chat input to mention files and inject them as context.\n\nDownload the latest release from the [Releases](/ContegoCode/Quanta-Code-Editor/releases) page. Extract and run — no build tools required.\n\nQuanta's agent has access to **30+ tools** organized into functional groups:\n\n| Tool | Description |\n|---|---|\n`read_file` |\nRead file contents with line numbers (10MB limit, outline for large files) |\n`write_file` |\nCreate or overwrite files atomically (auto-creates parent dirs) |\n`edit_file` |\nFind-and-replace edits with multi-strategy matching (exact, fuzzy, ellipsis) |\n`apply_diff` |\nApply unified diffs with 7-strategy flexible patching |\n`list_directory` |\nList directory contents (dirs first, then files, alphabetical) |\n`find_path` |\nGlob-based file search (`**/*.rs` , respects .gitignore) |\n`grep` |\nRegex content search across files (with context lines, pagination) |\n`terminal` |\nExecute shell commands (safety guards, streaming output, sandbox support) |\n`create_directory` |\nCreate directories recursively |\n`delete_path` |\nDelete files or directories (blocked in Code mode for safety) |\n`copy_path` |\nCopy files or directories recursively |\n`move_path` |\nMove or rename files (atomic when possible) |\n\n| Tool | Description |\n|---|---|\n`diagnostics` |\nGet LSP errors/warnings with freshness tracking and tree-sitter fallback |\n`go_to_definition` |\nJump to symbol definition via reverse RPC to VS Code |\n`find_references` |\nFind all references to a symbol across the project |\n`get_code_actions` |\nGet available quick fixes and refactorings |\n`apply_code_action` |\nApply a code action with edit tracking and staleness checks |\n`rename_symbol` |\nRename a symbol across the entire workspace |\n\n| Tool | Description |\n|---|---|\n`git_status` |\nShow working tree status with branch info |\n`git_diff` |\nShow staged or unstaged changes |\n`git_commit` |\nStage and commit changes (auto-creates .gitignore if missing) |\n`git_branch` |\nCreate, switch, or list branches |\n`git_log` |\nShow recent commit history |\n`git_stash` |\nStash, pop, or list stashes |\n\n| Tool | Description |\n|---|---|\n`spawn_agent` |\nSpawn synchronous or async sub-agents (up to 3 levels deep) |\n`create_thread` |\nCreate independent background conversation threads |\n`check_subagent` |\nCheck status and retrieve results from async sub-agents |\n`list_agents_and_models` |\nList available agents and models |\n\n| Tool | Description |\n|---|---|\n`fetch` |\nHTTP GET with HTML-to-Markdown conversion |\n`image_search` |\nSearch the web for images (DuckDuckGo, no API key) |\n`skill` |\nLoad engineering skills from project, global, or built-in sources |\n`tool_search` |\nOn-demand deferred loading of MCP tools |\n`write_plan_file` |\nWrite implementation plans in Plan mode |\n`undo_edit` |\nUndo the most recent accepted edit to a file |\n`todo_list` |\nPersistent task tracking across conversation turns |\n\n| Mode | Capabilities | Use Case |\n|---|---|---|\nCode |\nFull toolset (except `delete_path` ) |\nBuilding features, fixing bugs, refactoring |\nAsk |\nRead-only (no file writes, no terminal) | Understanding code, asking questions |\nPlan |\nRead-only + `write_plan_file` |\nPlanning before implementing |\n\nSwitch modes using the mode button in the chat header.\n\nQuanta provides deep LSP integration that feeds real-time diagnostics to the model:\n\n**Push-based diagnostics**— VS Code sends diagnostics to the backend cache as they change** Per-file version tracking**— Ensures diagnostics are fresh and correctly scoped** Deduplication**— Merges diagnostics from multiple sources (LSP, tree-sitter)** Auto-refresh**— Diagnostics are re-fetched after agent file edits** Tree-sitter fallback**— Syntax-based diagnostics for languages without an LSP** Language-specific configuration**— Auto-configures LSP servers for 20+ languages\n\n**Supported LSP features:**\n\n- Diagnostics (errors, warnings, info, hints)\n- Go to definition\n- Find references\n- Code actions (quick fixes, refactorings)\n- Apply code action (with edit tracking)\n- Rename symbol (workspace-wide)\n\n**Auto-configured languages:** C#, TypeScript/JavaScript, Rust, Python, Go, Java, Kotlin, Dart, Ruby, F#, Erlang, Haskell, D, R, LaTeX, and more.\n\nQuanta creates automatic **workspace-level snapshots** using a shadow git repository — completely separate from your project's own git repo.\n\n**Automatic**— A checkpoint is saved before every agent write action** Works without git**— Your project doesn't need to be a git repo** Workspace-level**— Covers edits, deletes, moves, and terminal-generated changes** Browseable**— View checkpoint timeline with messages and timestamps** Restorable**— Revert the entire workspace to any checkpoint** Diffable**— Compare any checkpoint against current state or another checkpoint** Deletable**— Select and delete individual checkpoints or all at once** Safe**— Checkpoints are stored in`~/.quanta/checkpoints/`\n\nand never touch your project\n\nEvery agent edit is tracked in a per-edit history with full undo/redo support:\n\n**Diff preview**— See exactly what changed before accepting** Accept/reject individually**— Review each edit one at a time** Accept/reject all**— Bulk operations for multi-file changes** Undo**— Revert specific edits after they've been applied** Redo**— Re-apply undone edits** Full diff view**— Open a complete diff in a separate editor panel** Edit history panel**— Timeline of all edits in the current session\n\nQuanta supports the [Model Context Protocol](https://modelcontextprotocol.io) for extending the agent with external tools:\n\n| Server | Tools | Description |\n|---|---|---|\nJina AI |\n20 | Web reading, search, screenshots, academic search (arXiv/SSRN), image search, reranking, classification, PDF extraction. Requires Jina API key. |\nGitHub |\n7 | Search repositories, read files, create issues, list issues, create PRs, create branches, push files. Requires GitHub token. |\nFilesystem |\n6 | Read, write, list, create, move, and search files on the local filesystem. No API key required. |\nFetch |\n1 | Fetch web pages and convert HTML to markdown. Requires uvx (Python). No API key required. |\nGit |\n5 | Git status, diff, log, commit, and branch management. Requires uvx (Python). No API key required. |\nSequential-thinking |\n1 | Structured step-by-step reasoning with branching, revision, and dynamic thought count. Recommended for Plan mode. |\nMemory |\n4 | Persistent knowledge graph — create entities, relations, search nodes, read graph. |\nHuggingFace |\n4 | Search models, get model info, list model files, download models. Requires HF token. |\nSerena |\n7 | Semantic code analysis via LSP — find symbols, references, get details, replace symbol bodies, insert code before/after. Requires uvx. |\nPlaywright |\n6 | Browser automation — navigate, click, fill, screenshot, evaluate JS, select options. Official Microsoft server. |\nArxiv |\n5 | Search arXiv papers (free-text, author, category), get full metadata, list subject categories. |\nAugments |\n7 | Coding research — API docs, code examples, version comparisons, migration guides, error diagnosis, dependency scanning. Optional GitHub token. |\nPlantUML |\n4 | Generate UML diagrams (sequence, class, activity, and more) from text descriptions. |\nContext7 |\n2 | Up-to-date library and framework documentation fetched live from the source. |\n\n**On-demand tool loading**— MCP tools are deferred until needed, reducing context overhead by ~85%** Custom server configuration**— Add any MCP-compatible server** API key management**— Securely store credentials for MCP servers** Server status monitoring**— See connection status at a glance** Tool search**— The agent can search for and load MCP tools by keyword\n\nRoute different models to different tasks for optimal performance:\n\n| Task | Config Setting | Description |\n|---|---|---|\n| Main chat | `quanta.defaultModel` |\nPrimary model for agent conversations |\n| Sub-agents | `quanta.subagentModel` |\nModel for spawned sub-agents |\n| Summarization | `quanta.summarizationModel` |\nModel for auto-generating conversation titles |\n| Inline completion | `quanta.inlineCompletion.model` |\nCoder model for FIM completions |\n\nFine-tune each model individually via the Local Model Override Settings panel (`~/.quanta/model_overrides.json`\n\n):\n\n| Setting | Options | Description |\n|---|---|---|\n| Think level | Low / Medium / High | Reasoning depth for thinking models |\n| Temperature | 0.0–2.0 | Sampling temperature |\n| Top-p | 0.0–1.0 | Nucleus sampling threshold |\n| Top-k | 1–100 | Top-k sampling |\n| Num predict multiplier | 1x–10x | Scale max output tokens |\n| Tool call mode | Parallel / Sequential | How the model calls tools |\n| Edit format | WholeFile / UnifiedDiff / FindReplace | Preferred file editing strategy |\n| Context window | Custom | Override the model's context length |\n| Prefer write_file | On / Off | Prefer whole-file writes (with fallback to edit/diff) |\n| Preserve thinking | On / Off | Keep thinking content during context compaction |\n| Max empty retries | 1–10 | Retries for empty completions (thinking models) |\n| Max unfinished retries | 1–10 | Retries when LSP errors remain |\n\n**Override priority:** User override > Built-in profile > Baseline defaults\n\nBrowse and install models directly from HuggingFace without leaving the editor:\n\n**Search**— Find GGUF models by name, filter by pipeline tag and size** Sort**— By downloads, likes, or relevance** Download**— GGUF files or safetensors directories with progress tracking** Auto-register**— Downloaded models are automatically registered with Ollama** Hardware specs**— Detects CPU, RAM, GPU VRAM to help you pick the right model** Cleanup**— Tracks and removes orphaned blobs from cancelled downloads** Model management**— View and delete locally installed models\n\nQuanta includes **20+ built-in engineering skills** that provide structured guidance for common development tasks:\n\n| Skill | Description |\n|---|---|\n`help` |\nGet help with Quanta features and commands |\n`implement` |\nImplementation guidance for features |\n`init` |\nInitialize a new project with Quanta |\n`setup-project` |\nConfigure project with issue tracker |\n`wayfinder` |\nNavigate and understand a codebase |\n`triage` |\nTriage and prioritize issues |\n`to-spec` |\nConvert requirements to specifications |\n`to-tickets` |\nConvert specifications to tickets |\n`grill-with-docs` |\nValidate code against documentation |\n`improve-codebase-architecture` |\nSystematic architecture improvement |\n\n| Skill | Description |\n|---|---|\n`tdd` |\nTest-driven development with mocking |\n`code-review` |\nStructured code review |\n`security-review` |\nSecurity vulnerability review |\n`diagnosing-bugs` |\nSystematic bug diagnosis |\n`deep-research` |\nDeep research methodology |\n`research` |\nGeneral research approach |\n`prototype` |\nPrototyping (logic + UI) |\n`domain-modeling` |\nDomain modeling with ADRs |\n`codebase-design` |\nArchitecture design (Design-It-Twice) |\n`simplify` |\nCode simplification |\n`verify` |\nVerification strategies |\n`resolving-merge-conflicts` |\nMerge conflict resolution |\n`webapp-testing` |\nWeb application testing |\n`grilling` |\nCode quality grilling |\n\nCreate your own skills in:\n\n**Project-local:**`.agents/skills/{name}/SKILL.md`\n\n**Global:**`~/.agents/skills/{name}/SKILL.md`\n\n- integration (tiny.en, base.en, small.en models)\n- Configurable language\n- Dictation toggle:\n`Ctrl+Shift+M`\n\n- Audio buffer processing with temporary file handling\n\n- integration with voice model downloads from HuggingFace\n- Configurable voice (e.g.,\n`en_US-lessac-medium`\n\n) - Speed control\n- Read aloud toggle:\n`Ctrl+Shift+L`\n\n- Markdown cleaning for natural speech\n- Voice listing (installed and available)\n\n- Create, list, load, and delete sessions\n- Auto-generated conversation titles\n- Search sessions by content\n- Per-session and cumulative token usage tracking\n- Session persistence to disk\n- Cascade delete for sub-agent sessions\n\n**Export** to Markdown, JSON, or PDF**Import** from JSON or Markdown- Exports include thinking content, tool calls, and timestamps\n\nPlan before you build:\n\n- Switch to\n**Plan mode** in the chat header - Ask Quanta to create an implementation plan\n- Review the rendered markdown plan in the plan panel\n- Click\n**Implement Plan** to switch to Code mode and execute - Edit the plan at any time via\n**Edit Plan**\n\nPlan files are saved to `.quanta/plans/`\n\nand persist across sessions.\n\n| Setting | Default | Description |\n|---|---|---|\n`quanta.serverHost` |\n`127.0.0.1` |\nBackend server host |\n`quanta.serverPort` |\n`8080` |\nBackend server port |\n`quanta.serverPath` |\n`\"\"` |\nCustom path to backend binary |\n`quanta.autoStartServer` |\n`true` |\nAuto-start backend on activation |\n\n| Setting | Default | Description |\n|---|---|---|\n`quanta.defaultModel` |\n`\"\"` |\nDefault model (empty = first available) |\n`quanta.subagentModel` |\n`\"\"` |\nModel for sub-agents |\n`quanta.summarizationModel` |\n`\"\"` |\nModel for title generation |\n\n| Setting | Default | Description |\n|---|---|---|\n`quanta.inlineCompletion.enabled` |\n`true` |\nEnable inline completions |\n`quanta.inlineCompletion.model` |\n`\"\"` |\nOverride completion model |\n`quanta.inlineCompletion.debounceMs` |\n`300` |\nDebounce delay |\n`quanta.inlineCompletion.maxContextLines` |\n`100` |\nContext lines to send |\n`quanta.inlineCompletion.minPrefixChars` |\n`3` |\nMinimum prefix to trigger |\n\n| Setting | Default | Description |\n|---|---|---|\n`quanta.autoApproveEdits` |\n`false` |\nAuto-approve without diff preview |\n`quanta.terminalSandbox` |\n`false` |\nTerminal sandbox mode |\n\n| Setting | Default | Description |\n|---|---|---|\n`quanta.treeSitterFallback` |\n`true` |\nTree-sitter syntax linting fallback |\n`quanta.diagnosticsWaitMs` |\n`2000` |\nLSP diagnostic wait time |\n\n| Setting | Default | Description |\n|---|---|---|\n`quanta.speechToText.enabled` |\n`false` |\nEnable speech-to-text |\n`quanta.speechToText.language` |\n`en` |\nLanguage code |\n`quanta.textToSpeech.enabled` |\n`false` |\nEnable text-to-speech |\n`quanta.textToSpeech.speed` |\n`1.0` |\nSpeech speed |\n\nMIT License — see [LICENSE](/ContegoCode/Quanta-Code-Editor/blob/main/Extension/LICENSE) for details.\n\nCopyright (c) 2026 Quanta AI\n\n**Quanta AI** — Local-first AI coding, powered by Rust and Ollama.", "url": "https://wpnews.pro/news/quanta-ai-code-editor", "canonical_source": "https://github.com/ContegoCode/Quanta-Code-Editor", "published_at": "2026-08-28 23:55:38+00:00", "updated_at": "2026-08-29 00:17:55.514815+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "ai-agents", "artificial-intelligence"], "entities": ["Quanta", "VS Code OSS", "Ollama", "OpenAI", "Anthropic", "Cursor", "Claude Code", "Zed AI"], "alternates": {"html": "https://wpnews.pro/news/quanta-ai-code-editor", "markdown": "https://wpnews.pro/news/quanta-ai-code-editor.md", "text": "https://wpnews.pro/news/quanta-ai-code-editor.txt", "jsonld": "https://wpnews.pro/news/quanta-ai-code-editor.jsonld"}}