The IDE for the agent era

The first IDE built for agents —
where developers and the business build together.

Two firsts in one tool. An agent lifecycle that lets you build, eval, replay, and ship agents in one place — and a workspace where engineers and business users align at the development stage, not three sprints later when the customer complains.

Powered by Smart-Code: no API keys, no model-picking — we route to the right model per task and you start coding instantly. 500 credits free for 30 days, then $9.99/mo, or free forever on local Ollama.

What no other IDE does

Three things that make CodeNow structurally different.

Two structural firsts — built for agents and devs + business co-building — with Smart-Code as the zero-friction way in.

The on-ramp · v0.1.54 Powered by Smart-Code · with Token Economics

Start in 30 seconds.
No keys. No model-picking.

Smart-Code is the easy way in — for developers and business users alike. It picks the right model for the question you just asked. Claude when you want fast. Codex when you need deep. Automatic cross-lab failover, a live token meter, always the right one. Never your problem.

C Claude Haiku 4.5 Fast coding brain + G OpenAI GPT-5 Codex Deep reasoning brain

No API keys · 500 credits free for 30 days · then $9.99/mo · or stay free forever on Local · Ollama (offline)

30-second setup — we auto-detect your existing tools
For developers

Build any agent.
Any stack.

  • Build with any harness — Claude SDK, Cursor SDK, Microsoft Agent Framework, Google ADK
  • Agent Foundry: Run · Trace · Evals · Tools · Prompts · Replay
  • Replay any production run, fork to your current code, side-by-side diff
  • Real terminal, real deploys, real tools — publish to Agent21
See Agent Foundry →
For business users

Manage any agent.
No code.

  • Import agents from Agent21 marketplace, HTTP, or your dev team
  • Skillify with company-specific domain knowledge
  • Visual guardrails sent as system prompt on every run
  • Monitor, override, and publish to monetize on Agent21
See Human Oversight →
The second first —

Engineering and the business stop fighting misalignment.

On every other team, the business writes a spec, engineering builds for three sprints, and the gap only surfaces when the customer complains. CodeNow is the first IDE where the domain expert and the engineer work the same agent, in the same project, while it's being built — skilling it, guard-railing it, and watching runs together. Alignment moves to the development stage, where it's cheap to fix.

Free for 1 project & 1 AI model — no credit card. Paid tiers from $9.99/seat/month.

Pick Apple Silicon for M1/M2/M3/M4, or Intel for older Macs. Linux also available.

First-class scaffolds for the agent SDKs your enterprise already runs
Trusted Agent Deploy ships to
Vercel live in v0.1.26 AWS / Azure / GCP live in v0.1.35 On-prem Kubernetes live in v0.1.35
CodeNow — six projects in one window: Acme Corp, ABC Corp, Beta Bank, Customer Portal, Internal Tools Switch AI models in one click: Claude Code, OpenAI Codex, Gemini, Aider, GitHub Copilot Executive Mode — domain experts train AI agents without code Per-project connections: each project sees only its own Jira, Slack, Salesforce, and Workday
The one frame no competitor can screenshot back

Replay any production run. Fork it to your code. See the diff — before your customer does.

Your agent worked in production last week. You changed the code today. Did you just break it? Every CodeNow run — local and production — is captured step by step: prompt, tool calls, model response, cost, tokens, latency. Click Fork to current code, and CodeNow re-runs that exact production input against the code on your machine right now, side-by-side with the original. No Langfuse tab. No Helicone account. No midnight pytest harness. No duct tape — it's in the editor where you already work.

30-second setup

Open it. We've already imported your setup.

On first launch, CodeNow scans your machine for credentials and configs from the tools you already use. One click — your AI keys, GitHub auth, git identity, and project remotes are all wired up.

VSVS Code
CuCursor
CCClaude Code
CxCodex CLI
GmGemini
AiAider
CoContinue
ghgh CLI
GLglab CLI
JrJira (Atlascode)
git~/.gitconfig & SSH
env.env & env vars
Nothing imports without your click. All scanning happens locally — values never leave your machine. Imported keys land in your OS keychain (Keychain on macOS, Credential Manager on Windows). Source available for enterprise audits under NDA — email karl@codenow.pro.
Why developers switch

Three reasons devs switch from VS Code and Cursor.

  1. Replay a production agent run and fork it into your current code — with a side-by-side diff. No one else ships this.
  2. Run 4–6 projects — each with its own model, terminal, and MCP connections — in one window.
  3. Your business teammate skills, guardrails, and oversees the same agent you're building — live, in the same project.

The full comparison, row by row → Everything Cursor, Windsurf, Codex & Zed do, plus the agent + oversight layer they don't. As of v0.1.54 CodeNow ships SMART-Code with Token Economics — a multi-model coding agent that auto-routes between Anthropic Haiku 4.5 (speed) and OpenAI GPT-5 Codex (depth) per task, now with open-weight Kimi K2 + Qwen coders (Fireworks) selectable across SMART-Code, Cmd+K, autocomplete & the multi-model Studio, drag-portable Agent Foundry agents, screenshot/vision input, and cross-agent context continuity (all v0.1.54), with automatic cross-lab failover (if one lab is down or over quota, your turn lands on the other — no dead turns), cache-stable context blocks + per-turn cache-hit % surfaced in the routing drawer. The Token Economy Index measures $ per resolved task — the metric nobody else publishes. No model-picking. Metered in credits (1 credit = 1,000 tokens) — 500 free for 30 days, then from $9.99/mo; credits only meter CodeNow-served inference, and BYOK is always free. CodeNow also ships TrustModel AGP as built-in agent-governance — every agent in your Fleet gets a TrustScore from minute one (no separate signup, no separate bill). Plus full parity on the IDE essentials — Cmd+P, Cmd+Shift+F, command palette, @ mentions, Apply, Tab autocomplete, codebase Q&A, source-control GUI, Vim mode, real-time CRDT pair-programming (v0.1.28), Codex-style Task Hub (v0.1.32), CodeNow Sidecar (Mode C) pushing skills + guardrails into agents deployed in your own AWS/GCP/Azure cloud (v0.1.28), Agent Fleet auto-detection across every project (Claude Agent SDK · OpenAI Agents · Google ADK · Microsoft Agent Framework · LangGraph · CrewAI · MCP — v0.1.44), built-in agents (SMART-Code · Composer · Cmd+K — v0.1.44), import any MCP server or CLI agent into Business mode (v0.1.49), browser-as-agent-tool (navigate/eval-js/get-dom/console — v0.1.42), cross-agent context via memory.jsonl ledger (v0.1.42), open-tab + chat-history persistence across restarts (v0.1.46), Live Agent Replay, anonymous read-only share links, channel-separated prompt-injection defense, SHA-256 Merkle audit trail, Cisco DefenseClaw runtime (partnership →), mobile companion app at codenow.pro/app that can drive your desktop's live SMART-Code loop from your phone (Desktop Relay — v0.1.50), one-click deploy to Vercel / K8s / AWS / Azure / GCP, and the only Human Oversight surface for non-engineers — all in one window.

Capability CodeNow Cursor Windsurf Codex CLI Zed VS Code
Core IDE features (parity as of v0.1.7)
Cmd+P fuzzy file finderCLI — n/a
Cmd+Shift+F project-wide searchgrep/rg
Cmd+Shift+P command paletteCLI — n/a
Inline edit (Cmd+K) with streaming diffCLI promptAgent panelvia Copilot
Multi-file agentic edit (Cmd+I / Composer)CascadeAgent panelNo
@ mentions for file / URL context in chatvia stdinNo
"Apply" button on AI-suggested code blocksCLI — n/aNo
Tab autocomplete (ghost text)CLI — n/aZeta (open-weight)via Copilot
Codebase Q&A panel ("Ask the repo")Cascadevia promptsAgent threadNo
Source-control GUI (stage / diff / commit)CLI — n/a
Real terminal (no sandbox)✓ (it IS the terminal)
Where CodeNow goes further
CodeNow Smart Coding — dual-lab coding agent that auto-routes between Anthropic Haiku 4.5 (speed) and OpenAI GPT-5 Codex (depth) per task. No model-picking. 30 days free with 50K tokens/day across both, then $9.99/mo. Read the pitch →Yes (v0.1.35)Single-lab (Anthropic OR OpenAI)Single-labSingle-lab (OpenAI)Single-lab (hosted)No
Built-in agent — no API key required — bundled in $9.99 sub via cloud proxy (Anthropic + OpenAI keys provided by us) OR fully offline via local Ollama. Both included.Yes (v0.1.34)Bundled cloud onlyBundled cloud onlyOpenAI account requiredBundled cloud onlyBYOK only
CodeNow Sidecar (Mode C) — push skills + guardrails into agents deployed in your own AWS/GCP/Azure cloud; outbound long-poll, no inbound firewall holes (Docker image, k8s manifest, hardened systemd all shipping)Yes (v0.1.28)NoNoNoNoNo
Pair-programming with live CRDT cursors — Yjs + Supabase Realtime, both devs editing the same file with presence; no screen-share requiredYes (v0.1.28)Workspaces (no live cursors)LimitedNo (CLI)YesLive Share
Audit-log forwarding from customer cloud — sidecar accepts agent runs on loopback, forwards to CodeNow tagged with sidecar_id; closes the runs loop for Mode C agentsYes (v0.1.28)NoNoNoNoNo
7-day trial counter + Stripe checkout in app — "Day N of 7 · Upgrade" pill in topbar opens $9.99 Payment Link; webhook flips plan automaticallyYes (v0.1.29)NoNoNoNoNo
Model Arena — every flagship model answers the same prompt side-by-side; "Pick winner" persists as adoption signalYes (v0.1.20)NoNoNoNoNo
Provider transparency drawer — every API call logged with cost, tokens, latency, cache hits. No silent reroutingYes (v0.1.20)NoNoNoNoNo
Capability tuning per-provider — surface each lab's premium knobs (extended thinking, reasoning effort, web grounding) per-projectYes (v0.1.20)NoNoNoNoNo
Anonymous read-only share link — mint URL, recipient clones & opens project in viewer mode (Monaco read-only + revoke)Yes (v0.1.21)NoNoNoNoLive Share (requires install + sign-in)
Multi-project tabs in one windowYesNoNoNoNoNo
Switch AI models in one click — 5+ models side-by-side5+ modelsCursor onlyCascade onlyNoparallel agents (single thread)via extensions
Cross-LLM knowledge portability — one source emits CLAUDE.md, AGENTS.md, GEMINI.md, .aider.conf.ymlYesNoNoNoNoNo
Agent Foundry — Run/Trace/Evals/Tools/Prompts panel for agent-buildingYesNoNoNoNoNo
Live Agent Replay — every run captured, replayable, forkable to current codeYesNoNoNoNoNo
Multi-harness scaffolds (Claude · Cursor · Microsoft · Google ADK)4 SDKsCursor SDKNoNoACP — bring-your-ownNo
Per-project MCP connections (49 vetted, hosted & local)YesGlobal onlyGlobal onlyNoGlobal onlyGlobal only
API keys encrypted in the OS keychainuser configuser configNouser configuser config
Detects existing CLI auth (codex / gemini / claude) automaticallyNoNoNoNoNo
Prompt caching (cache_control: ephemeral) across providersYesNoNoNoNoNo
Channel-separated prompt-injection defense (<untrusted-data> wrap)YesNoNoNoNoNo
SHA-256 Merkle hash chain over JSONL audit trailYesNoNoNoNoNo
Cisco DefenseClaw runtime (Skills/MCP scanner + Guardrail Proxy)YesNoNoNoNoNo
Embedded browser control — AI navigates, clicks, types, scrolls, screenshots the built-in browser panelYes (v0.1.35)NoYesNoNoNo
Mobile companion app — review runs, approve trust gates, edit skills from your phoneYes (v0.1.35 — codenow.pro/app)NoYesNoNoNo
JIRA → multi-model context — click a ticket, all agents (Claude/Codex/Gemini) receive full ticket context automaticallyYes (v0.1.35)NoNoNoNovia extensions
One-click deploy to Vercel / AWS / Azure / GCP / K8s — signed TrustScore artifact + GitHub Action wrapperYes (v0.1.26–27)NoNoNoNoNo
Human Oversight for Agents (PMs, Ops, HR, Finance, Sales, Marketing, Legal, CX, Executives)
Train — domain expert teaches the agent (Skillify, no code)YesNoNoNoNoNo
Guardrail — visual rules enforced as system prompt on every runNoNoNoTool permissionsNo
Monitor — every run captured with input/output/TrustScoreNoNoNoNoNo
Override — pause, replay, or yank a deployed agent in one clickNoNoNoNoNo
Dev + business user side-by-side on the same agentYesNoNoNoNoNo
Workforce view — humans + agents in one panelNoNoNoNoNo
TrustScores on every agent outputNoNoNoNoNo
One-click publish to Agent21 marketplaceYesNoNoNoNoNo
Where Zed goes further today (CodeNow roadmap)
Real-time CRDT collab (live cursors, simultaneous edits)Yes (v0.1.8 — Yjs)NoNoNoYesLive Share
Voice / video pair-programmingVia Slack / Discord / Zoom integrationNoNoNoBuilt-inLive Share
First-class Vim modeYes (v0.1.8 — monaco-vim)via extensionvia extensionNoYes (native)via extension
Slack-style team channels in the editorYes (v0.1.8)NoNoNoYesNo
GPU-rendered native (Rust) — 120fps editingElectron + MonacoElectronElectronNoYes (Rust)Electron
Editor + agent open sourceWiki public; IDE source closedNoNoNoEditor + Zeta + ACPYes
Tech ↔ Non-Tech Collaboration
One tool for engineers and any business userYesNoNoNoNoNo
Engineering ↔ business handoff in same workspaceNoNoNoNoNo
Audit trail of who trained / guard-railed / overrode each agentNoNoNoNoNo
Pricing & token economics
Bundled coding agent — included in subscription, no API keysYes (Claude + Codex auto-routed)Yes (single lab)Yes (single lab)OpenAI account requiredHosted (single lab)No
Free trial — try before paying30 days · 50K tokens/day · both labsFree tier: very limitedFree tier: very limitedNo standalone trialFree editor (paid models)Free editor
Token spend transparency — see your daily usage liveLive meter · per-day reset · which lab answered each turnOpaque credit pool drainsOpaque quota burnYour OpenAI dashOpaque hosted billingvia your own extension
Multi-lab side-by-side — Claude AND Codex in one agent, auto-pickedYes — Smart routing per turnSingle-lab (pick at sub time)Single-labOpenAI onlySingle-labNo
BYOK still available — bring your own keys for premium models (Opus / GPT-5 / Gemini 2.5)Yes — per-provider tabs (Claude Code · Codex · Gemini · Aider · Copilot)Yes, but Tab autocomplete still needs Pro subIndividual users only · certain models · not TeamsYes (OpenAI native)Hosted-only by defaultYes
Local mode — fully offline · zero connectivity · unlimitedYes (Ollama · always free)NoNoNoNovia Continue extension
Subscription cost500 credits free for 30 days · then $9.99/mo (Developer Pro) · $29.99 (Business) · $39/seat (Team)$20/mo Pro · $60/mo Pro+ · $40/seat Business$20/mo Pro · $200/mo Max · $40/seat TeamsChatGPT Plus / API onlyFree editor · paid hosted modelsFree
Why $9.99/mo — and what it gets you

Two top labs (Claude + Codex), auto-routed per task, bundled in. Plus the IDE.

30 days free · 50K tokens/day · both labs

Try with no credit card, no API keys. CodeNow's hosted proxy puts both Anthropic Haiku 4.5 and OpenAI GPT-5 Codex at your fingertips, with daily reset. After 30 days, $9.99/mo to keep both labs — or stay free forever on Local (Ollama, offline).

Smart routing, not model-picking

Cursor & Windsurf make you pick a model per turn. We pick for you in milliseconds — fast Claude for chat-like questions, deep Codex for refactors and reasoning. See how →

Live token meter, no opaque drain

The chat panel shows your daily usage live — and tags every assistant message with the lab + model that answered. No "Pro+ credit pool drained" surprises. No black box.

Premium-model BYOK still works

Want Claude Opus or GPT-5 frontier or Gemini 2.5? Use the dedicated Claude Code, Codex, Gemini, Aider, Copilot bottom tabs — each runs the official CLI with your own keys. CodeNow Code Cloud is bundled; BYOK premium is parallel, not replacement.

Plus everything else $9.99 buys you: multi-project tabs · all 4 SDK scaffolds · Agent Foundry · Live Replay · Sidecar · Human Oversight surface · Task Hub · JIRA-in-IDE · pair-programming with CRDT cursors. CodeNow Smart Coding → · All release notes.

From Cursor · Codex · Windsurf · Copilot

Top 15 reasons devs are switching to CodeNow.

Beta users came from every IDE in the category. Here's what made them stay. Each one is a real complaint we've heard from devs running Cursor / Codex / Windsurf / Copilot daily — and how CodeNow handles it.

  1. 01

    Stop picking models. Forever.

    Cursor & Windsurf show a dropdown. CodeNow's Smart routing picks Claude for fast questions, Codex for hard ones — in milliseconds, automatically. You ask. We pick. You ship.

  2. 02

    Two labs in one bill — Claude + Codex.

    Every other IDE locks you to one lab. CodeNow bundles Anthropic Haiku 4.5 AND OpenAI GPT-5 Codex. One $9.99/mo. Auto-failover if either lab has an outage. Vendor lock-in is the old way.

  3. 03

    30 days actually free — 50K tokens/day.

    No credit card. No API keys. No "your free credits expired after 200 messages." 50K tokens/day across BOTH labs for a full month. Then $9.99 — half what Cursor or Windsurf charges.

  4. 04

    Multi-project tabs in one window.

    You work on 3 repos. Cursor wants 3 windows. Windsurf wants 3 windows. CodeNow gives you 3 tabs — each with its own AI model, terminal, MCP connections, agent state. Stop alt-tabbing.

  5. 05

    Codex-style task hub — every task is a branch.

    Sixth sidebar tab. Every agent task = own git branch (codenow/tsk-xxx), status pill (running / needs-review / merged), conversation, files-changed. Cross-project. Ask Claude to "fix X" and it lives as a Task you can review, merge, or discard. See Task Hub →

  6. 06

    Local mode — zero connectivity, fully offline.

    Install Ollama, click Local mode. Every keystroke, prompt, response stays on your laptop. No proxy, no telemetry, no daily cap, no monthly fee. Privacy-first devs love this. Cursor & Windsurf don't ship anything close.

  7. 07

    Live Agent Replay — fork any production run.

    Every agent run captured as JSONL. Click Fork to current code → to re-run any past prompt against your current state, side-by-side diff. Cursor doesn't have a replay system. Neither does anyone else.

  8. 08

    CodeNow Sidecar — agents in YOUR cloud.

    Push skills + guardrails into agents deployed in your own AWS / GCP / Azure VPC. Outbound HTTPS only, no inbound firewall holes. Docker image + k8s manifest + hardened systemd unit all ship. No other IDE has a customer-cloud agent push channel.

  9. 09

    All 4 SDK scaffolds — no harness lock-in.

    Build with Claude Agent SDK (TS or Python), Cursor SDK, Microsoft Agent Framework (Azure), or Google ADK (Vertex). One IDE, every harness. Pick the right tool for your enterprise stack, not whoever your IDE vendor partnered with.

  10. 10

    Real terminal — no sandbox theater.

    CodeNow's terminal is a real node-pty shell. npm test runs against your real Node. gcloud deploy talks to your real GCP. Cursor's terminal is wrapped; Codex CLI IS the terminal but lacks the IDE. CodeNow is both.

  11. 11

    49 vetted MCP integrations, per-project.

    GitHub · JIRA · Slack · HubSpot · Salesforce · Postgres · Stripe · 42 more. Scoped per project — your work repo doesn't share connectors with your personal sandbox. Cursor & Windsurf only support global MCP.

  12. 12

    Pair programming with live CRDT cursors.

    Yjs + Supabase Realtime — both devs editing the same buffer with presence indicators, no screen-share required. Cursor's Workspaces feature has no live cursors. Windsurf has limited collab. CodeNow shipped this in v0.1.28.

  13. 13

    JIRA tickets → multi-model context, one click.

    Click a JIRA ticket in the rail, all selected agents (Claude / Codex / Gemini) get the full ticket context — summary, priority, labels, description — at once. Stop pasting JIRA into chat. Branch auto-pin keeps your active ticket visible as you code.

  14. 14

    Built for everyone, not just engineers.

    Switch to Business mode — same window, no IDE chrome. Your PM trains agents via Skillify (no code), legal sets guardrails as toggles, ops monitors a Workforce panel, finance sees TrustScores on every run. Cursor / Windsurf / Codex are dev-only tools.

  15. 15

    Publish your agent to Agent21 with one click.

    Bundle prompts + evals + tools + guardrails + skills into a deployable package, list on the Agent21 marketplace, start earning. Built-in monetization. No other IDE has a path from "I built an agent on Friday" to "it's making money on Monday."

Tried Cursor or Windsurf? You'll feel the difference in 30 seconds.

Mac · Windows · Linux · signed & notarized · auto-updates · no credit card

Two paths to a marketplace agent

However the agent gets to your team — CodeNow takes it the rest of the way.

Whether your developers build it from scratch or your business user imports one from the Agent21 marketplace, the next steps are the same: skill it, guardrail it, monitor it, then list it back on Agent21 to monetize.

Path 1 · Built by your devs

Build → Manage → Publish

For agents your engineering team writes — running on your own GCP, Azure, AWS, Salesforce Agentforce, or wherever.
A

Build

Devs write the agent in Agent Foundry. Run / Trace / Evals / Tools / Prompts — any stack (Python, TS, Rust, Go), any LLM. The agent runs on your existing infra.

B

Invite a business user → Manage

Click Share → invite your domain expert as a collaborator. They open the same project, train it (Skillify), set guardrails, and monitor every run. Files in git, activity in Supabase — both sides see it live.

C

Publish to Agent21

One click in Agent Foundry bundles the manifest (prompts, evals, tool sigs, guardrail policy) and POSTs to the Agent21 marketplace. Your agent gets a public listing with provenance — built-by, runs-at, data access, price.

See how Studio handles this →
Path 2 · Imported by your team

Import → Manage → Publish

For agents that already exist — pulled from Agent21, an HTTP endpoint, or a vendor — that your business user wants to skill, oversee, and re-list.
A

Import

Browse the Agent21 catalog from inside CodeNow, paste an Agent21 URL, or wire up an HTTP endpoint. CodeNow registers the agent with full provenance — who built it, where it runs, what data it touches.

B

Manage (Skillify · Guardrail · Monitor · Override)

Your domain expert layers company-specific knowledge on top, sets guardrails, monitors every invocation. The base agent runs wherever it ran before — your overlay stays here.

C

Re-list on Agent21 to monetize

Publish your skilled, guard-railed version of the agent back to Agent21 — under a new slug, under your team's name, with your overlay baked in. Your domain expertise becomes a sellable layer on top of someone else's agent.

See Human Oversight →
Both paths converge at Agent21's agentic-company operations layer — where published agents get deployed under the right business function (CEO, CFO, CMO, Ops) and run alongside human counterparts.
Human Oversight for Agents

Your agents work for you — not the other way around.

Every business deploying AI agents has the same fear: drift. The agent gets clever in the wrong way. Hallucinates a number. Acts on stale data. Says something off-brand. CodeNow's Business mode is built so the human responsible for the work stays responsible — and stays in charge.

T

Train

Skillify lets a domain expert teach the agent the way the work actually gets done in your company. Every skill is versioned, attributable, and reversible.

G

Guardrail

Visual rules for data access, allowed actions, tone, escalation. Saved guardrails are sent to the agent as a system prompt on every invocation — so the human owner's policy is enforced, not assumed.

M

Monitor

Every agent run is captured with input, output, tools used, and a TrustScore. Review activity at human pace, not log-tail pace.

O

Override

One click to pause an agent, replay a prompt with a fix, or yank a deployed agent off its function. The human is always one click away from "stop."

Each business user can responsibly oversee 3–5 agents — meaning your AI workforce scales with the humans who own the outcomes, not separately from them. See the full Human Oversight story →
For Engineers

The IDE that finally scales past one repo.

Built for the engineers running 4–6 codebases at once. Vibe-coders, consultants, founders, agency teams.

📁

Multi-Project Tabs

All your projects as tabs in one window. No more 6 VS Code instances. Switch context instantly.

🤖

Multi-Model AI

Claude Code, OpenAI Codex, Gemini, Aider, Copilot. Switch between AI models with one click — per project.

🔁

Cross-LLM Knowledge Portability

Your project context, rules, memory, and skills live in one canonical bundle. CodeNow generates the right format for every AI CLI — CLAUDE.md, AGENTS.md, GEMINI.md, .aider.conf.yml. Switch from Claude to GPT-5 to Gemini without re-onboarding. The only IDE that survives an AI vendor change.

🔓

No Sandbox

Full system access. Push to GitHub, create Jira tickets, deploy to Vercel, send Slack messages. Everything your terminal can do.

🔐

Encrypted Secrets

API keys and access tokens encrypted at rest via your OS keychain (macOS Keychain, Windows DPAPI, Linux libsecret). Never written in plaintext, never echoed to your shell history.

🔌

MCP Connections

Built-in Jira, Slack, Gmail, GitHub, Stripe, Figma. Per-project connections — each project shows only what it uses.

Minimal UI

Not 47 menus. Not 200 settings. Just files, editor, terminal, and AI. Built for vibe-coders, not configuration warriors.

👥

Team Ready

Same IDE for everyone. Shared project configs. Engineers on Mac, Windows, and Linux all use the same tool.

New · Agent Foundry

The IDE for the agent era — not the SaaS era.

The first IDE built for agents. SDLC tools optimize for writing code. Agent Foundry models the loop after the code is written — Run, Trace, Evals, Tools, and Replay — so your agent isn't a script you hope works, it's a service you can prove works.

Cursor and VS Code optimize for writing code. Most builders today spend 80% of their time on the loop after they've written the agent — iterating prompts, eval-ing across models, debugging traces, testing tools. Agent Foundry is the panel none of them ship.

R

Run — three models, one click

Paste a prompt, fan it out to Claude Opus, GPT-5, and Gemini 2.5 in parallel. Side-by-side cards with response, latency, tokens. Stop guessing which model is best for the job.

T

Trace — see cost and timing

Every Run is auto-saved. Click any trace to inspect aggregate cost, fastest model, full system + user prompt, per-model output. Replay with one button. No browser-tab Helicone trip required.

E

Evals — test before you ship

JSON suites with six assertion types. Run-all against every model. Pass/fail diff vs your last run, so you catch regressions before the customer does. Snapshot a Run as an eval in one click.

Tools — test in isolation

Auto-discovers Python @tool and TS/JS tool defs across your project. Click Test, paste JSON args, see the real return. No more "let me write a 200-line test harness for one function."

P

Prompts — versioned, parameterized

Markdown files with frontmatter {{variables}}. Fill-in-modal substitution before Run. Every save is logged to history — diff today's prompt against last week's without ceremony.

Any harness — bring your own

Build with Claude Agent SDK, Cursor SDK (Composer 2 + multi-model), LangGraph, OpenAI Agents SDK, CrewAI, MCP, or raw fetch. Studio's eval/trace/replay/publish loop wraps your code — doesn't replace it. Cursor commoditized models. We commoditize harnesses.

Replay — production runs, replayable

Every agent invocation — local dev and Agent21 production — is captured as a step-by-step timeline. Tool calls, model responses, cost, tokens, latency. Click Fork to current code → to re-run the same input through your local agent and diff side-by-side. The screenshot Cursor can't ship: prod replay, not just dev sessions. Watch the 60-second demo →

Agent-building loop — head-to-head

What you actually need when you're shipping an agent, not a CRUD app.

Capability CodeNow Cursor VS Code Windsurf
Parallel multi-model invocation in one click No No No
Model Arena — same prompt to every flagship model with adoption-signal voting Yes (v0.1.20) No No No
Trace explorer with cost / tokens / latency per call No Extension No
First-class eval suite + pass/fail diff vs last run No No No
Tool isolation runner (test a single tool with JSON args) No No No
Prompt versioning with variable substitution No No No
Snapshot a successful run → eval test case (1 click) No No No
Stack-agnostic (Python / TS / Rust / Go / any SDK) TS-leaning TS-leaning
Replay any production run + Fork to current code Yes No No No
Multi-harness scaffolds (Claude · Cursor · Microsoft · Google · …) 4 shipped Cursor SDK only No No
Open auditable code (no black-box agent runtime) No No
Cursor's harness is the moat they shipped. Ours is the lifecycle around any harness — including theirs. We bundle Cursor SDK as a first-class kit, then handle the parts they don't: replay prod runs, fork to local code, eval against regressions, publish to Agent21.
Enterprise-ready · Microsoft + Google + Anthropic + Cursor

Every major harness, out of the box.

Pick the runtime your enterprise already standardized on. CodeNow ships first-class scaffolds for the harnesses Microsoft shops, Google Cloud shops, and AI-native teams actually use in production — with the same lifecycle (Test → Replay → Evals → Publish) wrapping all of them.

A

Claude Agent SDK

Anthropic · TypeScript + Python
Ready

The official Anthropic harness. Tool-use, MCP servers, subagents. Calls the API directly — no Claude Code CLI required.

Docs ↗ npm i @anthropic-ai/claude-agent-sdk
C

Cursor SDK

Cursor · TypeScript
New

Cursor's full agent harness — Composer 2 + any frontier model, sandboxed cloud VMs, subagents, hooks. Public beta. Drop into CodeNow's lifecycle wrapper.

Docs ↗ npm i @cursor/sdk
M

Microsoft Agent Framework

Microsoft · Python · Azure-native
New

Microsoft's official agent SDK (Semantic Kernel + AutoGen merged, v1.0 GA). Azure OpenAI native with AzureCliCredential or env-var auth. The default for the vast majority of enterprises living on Microsoft stack — Windows, Office, Azure, .NET for 50 years and counting.

Docs ↗ pip install agent-framework
G

Google ADK

Google · Python · Vertex AI native
New

Google's Agent Development Kit — workflows, agent teams, native Vertex AI deploy. Optimized for Gemini 2.0, model-agnostic. One env-var flip from AI Studio (local) to Vertex AI (production).

Docs ↗ pip install google-adk
L

LangGraph

LangChain · Python
Soon

Graph-based orchestration with cyclic flows, persistent state, checkpointing. The agent framework Python shops know.

O

OpenAI Agents SDK

OpenAI · Python
Soon

Handoffs, tracing, guardrails — OpenAI's official agent framework with first-class GPT support.

Cr

CrewAI

crewAI Inc · Python
Soon

Multi-agent crews with role-based collaboration. The framework when your "agent" is actually a team.

M

MCP Server

Anthropic · TS or Python
Soon

Expose your agent as a Model Context Protocol server. Plug into Claude, Cursor, CodeNow — anywhere MCP runs.

·

Empty manifest

CodeNow · any
Ready

No SDK, no opinions. Just an Agent21 manifest you wire to your own invocation URL. For the harness CodeNow doesn't ship yet.

One IDE, every harness. Don't bet your company on a single vendor's runtime. Switch harnesses by picking a different kit — same lifecycle, same eval suite, same publish flow, same prod replay.

Built in · No install

Trust, safety & observability — wired in by default.

Every agent built in CodeNow comes pre-wired to TrustModel.ai — replay, cost tracking, guardrails, audit logs, eval harnesses, HITL approvals. No SDK install. No separate setup. Sign in with CodeNow → land in TrustModel Console for fleet-wide monitoring.

See what's built in →
▶ Replay every run
$ Cost & tokens
⚐ Visual guardrails
✓ Eval harnesses
⏸ HITL approvals
⌖ Audit trail
Your AI, Your Choice

Five coding agents. One click to switch.

Each project remembers which model it uses. Use Claude for the React app, Codex for the Python service, Gemini for the docs.

Get started in 30 seconds

Download. Auto-import. Ship.

1

Download & open

Get CodeNow for your OS. Drag to Applications and launch.

2

Auto-import your setup

CodeNow scans for keys and configs from VS Code, Cursor, Claude Code, gh CLI, and more. One click imports the lot.

3

Pick your AI

Claude, GPT-5, Gemini, Aider — switch in one click. Your project knowledge follows you.

4

Connect & ship

One-click connect to Jira, GitHub, Slack, and more via MCP.

Pricing

The editor is free forever — full IDE, your own keys, local runs. Smart-Code is the easy on-ramp: start with no API keys (we pick the model and pay for the inference), 500 credits free for 30 days, then $9.99/mo — or stay free forever on local Ollama. Bring your own keys anytime, always $0 to us.

Editor
Free forever · every developer
$0
  • Full Developer-mode IDE — forever
  • Bring your own keys (BYOK) — Claude Code, Codex, Gemini, Aider, Copilot, side-by-side, $0 to us
  • Local agent runs (Replay, Recorder)
  • 500 SMART-Code credits free for 30 days (≈500K tokens)
  • Single user, no collaboration
Sign up free
Business
PMs · ops · sales · legal · finance · CX
$29.99/seat/mo
  • Business mode unlocked — Catalog, Skillify, Guardrails, Workforce, Output
  • 6,000 SMART-Code credits/mo (≈6M tokens)
  • Train agents with company-specific knowledge
  • Visual guardrail toggles (data scopes, action allowlists, TrustScore)
  • Real run log with TrustScores per call — for experts who oversee agents
Start as a Business user
Team
Mixed teams of devs + business users
$39/seat/mo
  • Both modes per seat — devs and business users in one workspace
  • Pooled SMART-Code credits across the team
  • Multi-user collaboration (shared knowledge, project sharing)
  • Admin panel + role management
  • Audit log of every agent run + override · priority support
Talk to us

Enterprise — starts at $99/seat/mo

SSO (SAML/OIDC), SOC 2 Type II attestation, on-prem / VPC deployment, contractual SLA, indemnification, dedicated CSM, training pack. Volume discounts above 50 seats.

Contact sales

How credits work

1 credit = 1,000 tokens. Credits only meter SMART-Code — the inference CodeNow serves and pays for. The Token Economy panel shows exactly what every task costs as it runs, so there are no surprises. Run out and you're never locked out: switch to your own API key (BYOK) and keep going free, or top up. Using your own keys is always $0 to us.

BYOK inference under your own provider keys is always free — we never mark it up. SMART-Code credits are billed monthly per the tier above. Cancel anytime; usage in the current billing period is honored. Terms · Privacy.