Cognition Devin v2 / Spec Mode
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.
At a glance
- Type
- Devin successor — autonomous coding agent + spec-mode (cross-listing)
- Tier
- T1
- Section
- Agent IDEs & coding harnesses
- Created
- 2024-03
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Free + paid; Spec Mode in Pro
- Funding
- $1.1B total $10.2B val Series E 2025-09
Taxonomy
- storage
- kv
- retrieval
- extraction-pull
- persistence
- cross-session
- update
- agent-controlled
- unit
- fact
- governance
- inspectable
- conflict
- llm-arbitrate
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 + Slack + REST
- Backend storage
- cloud session state + Knowledge
- Deployment
- Cloud
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- per-tenant
- MCP
- native (Devin MCP integrations)
- A2A
- searched not found
- OpenTelemetry
- searched not found
Similar systems
Other agent ides & coding harnesses in the catalog, ranked by inbound references.
- 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).
- Claude Code (Anthropic) T1
Anthropic's official agentic coding CLI — runs Claude as a long-running coding agent in the developer's terminal. Memory layer = CLAUDE.md (project + user scoped), agent skills, MCP servers. Released GA October 2024; widely adopted as the reference harness for Claude-as-coder. Plan Mode and Compute Use surfaces extend it from coding to broader desktop automation.
- 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.
- Aider (harness) T2
OSS terminal coding agent by Paul Gauthier — one of the original AI-pair-programmer CLIs (2023). Architect/Editor modes; repo-map for context; uses any LiteLLM-compatible model. Memory via CONVENTIONS.md and .aider.conf.yml — author-edited markdown. Distinct from the separate Aider memory-row in "Coding-agent memory"; this row characterises the harness itself.
- Amazon Q Developer T1
Amazon's developer-focused agent — formerly CodeWhisperer (renamed 2024-Q4). Available as IDE plugins (VS Code, JetBrains, Visual Studio, Eclipse), in AWS Console, and CLI. Strong AWS-tooling integration: Q can read CloudWatch, troubleshoot IAM, suggest AWS-SDK code. Companion to Kiro for spec-driven flows.
- Anthropic Computer Use T1
Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.
Related systems
References (2)
- Anthropic Claude (foundation models) depends on at runtime — adjacent-infrastructure cell: absorbed Windsurf IP (Aug 2025); Anthropic + OpenAI models
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — adjacent-infrastructure cell: absorbed Windsurf IP (Aug 2025); Anthropic + OpenAI models