Catalog Systems Agent IDEs & coding harnesses Cognition Devin v2 / Spec Mode

Cognition Devin v2 / Spec Mode

https://cognition.com/

Cross-listing of Cognition's Devin product framed at the harness level rather than the memory layer. Devin 2.0 (Mar 2025) added cheaper concurrent sessions; Spec Mode (Aug 2025, post-Windsurf-IP acquisition) integrates Windsurf-style spec authoring. The Coding-agent-memory row remains canonical for the memory framing.

Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 64 cited facts, 0 with a third-party source · 2 recorded changes · Suggest a correction

At a glance

Type
Devin successor — autonomous coding agent + spec-mode (cross-listing) vendor fix
Tier
T1
Section
Agent IDEs & coding harnesses
Created
2024-03 vendor fix
Latest release
Devin release notes update (2026-10-26) vendor fix
License
not applicable — not OSS fix
GitHub
not applicable — no GitHub repo fix
Pricing
Free $0; Pro $20/mo; Max $200/mo; Teams $80/mo plus $40/mo per full seat; Enterprise custom vendor fix
Funding
Over $2B Series E at $48B valuation (2026-09-08), led by Andreessen Horowitz and Accel with Founders Fund, General Catalyst and others vendor fix
Freshness
2026-10-29 fix
Layer
agent-infra repo fix
Licensing
commercial vendor fix
Deployment locus
hybrid vendor fix
Platform vs product
product vendor fix

When to use

Optimised for: fully autonomous SWE work + Spec Mode + Knowledge

Anti-fit: expensive per-session; not for non-coding

Pros & cons

Pros

Highest valuation in the category ($10.2B); only agent product to consolidate via M&A (Windsurf IP); enterprise customer logos are richest in category.

Cons

Cost per autonomous session is high; opaque pricing relative to seat-based competitors; M&A history creates roadmap risk.

Claims & capabilities

Devin 2.0 Mar 2025; Spec Mode Aug 2025; $400M raise at $10.2B val Sep 2025; absorbed remaining Windsurf IP Aug 2025.

Technical surface

API surface
Web app, Devin Desktop, Devin CLI, Slack and REST API
Backend storage
cloud session state + Knowledge
Deployment
Managed-only — Cognition cloud agents plus Devin Desktop and CLI; enterprise plan offers a dedicated deployment option
Embedding model
not applicable — not a memory product
Multi-tenancy
per-tenant
MCP
yes — MCP marketplace plus custom MCP servers (STDIO and remote) configurable in Devin; Devin also ships its own Devin MCP server
A2A
searched not found
OpenTelemetry
searched not found

Alternatives to Cognition Devin v2 / Spec Mode → live options ranked by shared design, licence, hosting and MCP support

Similar systems

Other agent ides & coding harnesses in the catalog, ranked by inbound references.

  • Claude Code (Anthropic) T1

    Anthropic's agentic coding tool: Claude as a coding agent in the terminal, IDEs (VS Code, JetBrains), desktop app, web/mobile, GitHub and Slack. Context via CLAUDE.md, skills, hooks, subagents and MCP servers.

  • Cursor (IDE) T1

    AI-first IDE that forked VS Code; Composer (multi-file edit) and Agent Mode (long-running coding agent) are its flagship surfaces. Memory layer = .cursorrules / Rules; recall via repo-aware Context Engine. Anysphere (parent) raised $900M Series C at $9.9B in May 2025; acquired by SpaceX (announced 2026-08-14, terms undisclosed), product continues under the Cursor brand.

  • OpenAI Codex CLI T1

    OpenAI's actively developed OSS terminal coding agent (Apr 2025), now written in Rust (codex-rs replaced the original TS CLI); also IDE extension + desktop app. Separate from the Codex Web cloud agent and the retired 2021 Codex model API. The codex mcp-server command (Codex as an MCP server) was deprecated on 2026-08-24 and removed in CLI 0.154.0 (2026-09-09); OpenAI points integrations to the experimental Codex app server, and codex mcp still connects Codex to external MCP servers.

  • Opencode (SST) T2

    SST team's open-source terminal coding agent — TypeScript, multi-model, MCP-native. Released 2025; explicitly positioned as a permissively-licensed Claude Code alternative. Memory via AGENTS.md (the emerging cross-harness convention).

  • Bedrock AgentCore (AWS) T2

    AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).

  • GitHub Copilot (Agent Mode) T1

    The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.

Sources (63 cited facts, 0 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-29
    • Homepage “https://cognition.ai” → “https://cognition.com/”
    #305
  2. 2026-10-27
    • Latest release “not applicable — not OSS” → “Devin release notes update (2026-10-26)” source
    • Pricing “Free + paid; Spec Mode in Pro” → “Free $0; Pro $20/mo; Max $200/mo; Teams $80/mo plus $40/mo per full seat; Enterprise custom” source
    • Funding / ownership “$1.1B total $10.2B val Series E 2025-09” → “Over $2B Series E at $48B valuation (2026-09-08), led by Andreessen Horowitz and Accel with Founders Fund, General Catalyst and others” source
    • Deployment “Cloud” → “Managed-only — Cognition cloud agents plus Devin Desktop and CLI; enterprise plan offers a dedicated deployment option” source
    • MCP support “native (Devin MCP integrations)” → “yes — MCP marketplace plus custom MCP servers (STDIO and remote) configurable in Devin; Devin also ships its own Devin MCP server” source
    #273

Related systems

References (2)