Catalog Systems Coding-agent memory Devin (Cognition)

Devin (Cognition)

https://devin.ai

Structured Knowledge items stored server-side. Three-tier scope: repo-pinned (always injected), global (recall by relevance), org/enterprise (visible to org members). Auto-generates Repo Knowledge from repo structure each session; reads past session trajectories for self-improvement; writes notes for recurring scheduled tasks.

Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 70 cited facts, 3 with a third-party source · 2 recorded changes · Suggest a correction

At a glance

Type
Server-side Knowledge + auto-Repo Knowledge vendor fix
Tier
T1
Section
Coding-agent memory
Created
2024-03 vendor fix
Latest release
not applicable — not OSS 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; Enterprise custom vendor fix
Funding
Series E ›$2B at $48B post-money (a16z/Accel, Sep 2026); prior Series D ›$1B at $26B (May 2026) 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
SDK languages
rest vendor fix
Protocols
mcp-client, mcp-server vendor fix
Compliance
ccpa, soc2-type2 vendor fix

Memory taxonomy

storage
kv
retrieval
injection
persistence
cross-session
update
agent-controlled
unit
fact
governance
inspectable
conflict
none

When to use

Optimised for: autonomous SWE work + structured Knowledge

Anti-fit: not for non-coding tasks; high cost per session

Pros & cons

Pros

Most aggressive memory model in the coding-agent space — explicit knowledge base + file-backed task notes + persistent terminal sessions.

Cons

Memory features only available inside the Devin product; not portable to other agents.

Claims & capabilities

$175M Series B at ~$2B (2024). Devin 2.0 announced Mar 2025.

Technical surface

API surface
REST, Slack integration
Backend storage
custom
Deployment
Both
Embedding model
locked
Multi-tenancy
Enterprise dedicated SaaS keeps customer data in customer tenant; on-prem and VPC deployment options available
MCP
via official adapter — Devin supports MCP servers
A2A
searched not found
OpenTelemetry
searched not found

Compare Devin (Cognition) with…

Alternatives to Devin (Cognition) → live options ranked by shared design, licence, hosting and MCP support

Similar systems

Other coding-agent memory in the catalog, ranked by inbound references.

  • Aider T2

    Appends conversation turns to .aider.chat.history.md in project root. restore_chat_history defaults to false — no automatic replay into new sessions. Community /session save command for JSON state snapshots. .aider.conf.yml carries static preferences.

  • Augment Code T1

    Real-time knowledge graph indexed from connected repos + commit history + CI/CD + tickets + docs. Separate Agent Memory layer (Sept 2025) captures session decisions/corrections/goals as discrete items with developer review/approval UI. MCP endpoint exposes the graph. Acquired by Harness (2026-10-08): Harness bought select Augment Code assets, including Cosmos, the Auggie CLI and the Context Engine, and the team joined Harness. augmentcode.com now leads with Cosmos, a software-factory agent platform.

  • Letta Code T3

    Letta's stateful coding-agent harness: agents rewrite their own memory blocks and skills, version context in git via MemFS (syncable to GitHub) and reflect via a periodic /sleeptime 'dreaming' process. from Letta (MemGPT) team. letta-ai/letta-code is now the main Letta source (harness, terminal UI, App Server, channels); the Letta V1 API server was retired to the archive branch of letta-ai/letta.

  • Replit Agent T1

    No documented built-in persistent semantic memory store. Session duration expanded to 200 min (Agent 3); Agent 4 shifts toward persistent runtimes. Temporal used for orchestration durability, not semantic memory. Cross-session memory relies on filesystem + agent-written notes.

  • agentmemory (rohitg00) T3

    Self-hosted persistent memory layer that captures coding-agent activity and recalls it in later sessions, positioned on public benchmark results. #7 in TeleAI Awesome-Agent-Memory

  • Beads (Steve Yegge) T3

    Dolt-backed, dependency-aware graph issue tracker that acts as persistent structured memory for coding agents, replacing markdown plans; `bd remember` stores durable facts and `bd prime` re-injects them.

Sources (69 cited facts, 3 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. 2026-10-23
    • Compliance “Encryption in transit and at rest; no customer data used for training by default (Enterprise: never trains); Trust …” → “Encryption in transit and at rest; no customer data used for training by default (Enterprise: never trains)” source
    #223
  2. 2026-10-22
    • Pricing “Free + paid” → “Free $0; Pro $20/mo; Max $200/mo; Teams $80/mo; Enterprise custom” source
    • Funding / ownership “$1.1B total $10.2B val Series E · 2025-09” → “Series E ›$2B at $48B post-money (a16z/Accel, Sep 2026); prior Series D ›$1B at $26B (May 2026)” source
    #219

Related systems

Referenced by (3)

  • Daytona integrates with — Daytona docs have a guide for running Devin (Cognition) with Daytona sandboxes. (verified 2026-10-29)
  • e2b integrates with — E2B docs have a Devin (Cognition) integration guide. (verified 2026-10-29)
  • HoneyHive integrates with — HoneyHive integrations docs have a Devin tracing/integration page. (verified 2026-10-29)