Sourcegraph Cody (agent)

https://sourcegraph.com/cody

Sourcegraph's coding assistant — IDE plugin (VS Code, JetBrains) plus web. Distinguishes itself with Sourcegraph's code-search index as the context provider (cross-repo, codebase-wide retrieval). Agentic chat added 2024; runs Claude / GPT / Gemini.

At a glance

Type
Code-intelligence-backed coding assistant + Agentic Chat
Tier
T1
Created
2023-02
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
Free + Pro $9/mo + Enterprise
Funding
Sourcegraph — $125M Series D 2021 ($2.6B val); profitable since 2023

Taxonomy

storage
graph
retrieval
similarity
persistence
long-term
update
extraction
unit
document
governance
inspectable
conflict
no

When to use

Optimised for: cross-repo code-search-backed context retrieval

Anti-fit: best ROI on big monorepos; less differentiated for small codebases

Pros & cons

Pros

Only coding agent with a real cross-repo code-search index behind it; on-prem deployment story is mature.

Cons

Sourcegraph indexing setup is heavyweight; agent surface lags Cursor / Cline on autonomous editing.

Claims & capabilities

Built by Sourcegraph; differentiator is cross-repo code search context; ~$150M ARR (reported) for parent.

Technical surface

API surface
VS Code + JetBrains plugins + web + CLI; API for codebase search
Backend storage
Sourcegraph code-graph + session state
Deployment
Cloud + on-prem
Embedding model
not applicable — not a memory product
Multi-tenancy
per-tenant (Enterprise)
MCP
searched not found
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)

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.