Home / Directory / AI SaaS tooling / Coding agents & developer tools / Sourcegraph
Sourcegraph
Developer platform spanning Amp (agentic coding with CLI and editor) and Sourcegraph Enterprise code intelligence, with Cody retained for enterprise customers.
Teams that want an agentic coding harness (Amp) with public pricing, or enterprises that already run Sourcegraph code search and need AI on large repos.
Buyers still expecting Cody Free/Pro self-serve chat, or orgs that only want a lightweight autocomplete plugin with a single flat seat fee.
Verdict
Sourcegraph remains a recommend for developers who want Amp's agentic workflow with honest public tiers, and for enterprises that pair code search with AI credits. Practitioners like the CLI-plus-editor model, subagents, and multi-model routing; polish still trails some rivals on day-one UX. Treat Cody as an Enterprise-only path after Free/Pro sunset, and budget Amp usage as credits that can climb on long threads.
Score Breakdown
How Sourcegraph scores in the categories that matter to its buyers.
Pricing
Sourcegraph's Amp agent publishes self-serve tiers on ampcode.com. Cody Free/Pro were discontinued in 2025; Cody continues only inside Sourcegraph Enterprise (sales quote). Prices below are USD from Amp's public pricing docs as of September 2026.
| Plan / product | Meter | Price (USD) | What stands out |
|---|---|---|---|
| Amp Hobby | Agent | $0 / mo + usage | Core agent features; pay-as-you-go credits and orbs |
| Amp Individual | Agent | $20 / mo | Included agent/orb allowances; BYOK options |
| Amp Teams | Workspace | No extra seat fee | Shared threads, pooled credits, member tiers |
| Amp Enterprise | Workspace | Sales quote | SCIM, audit logs, spend limits, FDE help |
| Sourcegraph Enterprise (Cody) | Platform | Sales quote | Code search + AI credits; no public self-serve Cody |
The Field at a Glance
Where Sourcegraph ranks among Coding agents & developer tools vendors we reviewed, by Overall Score and relative typical engagement cost.
Sourcegraph scores 8.3 beside Augment Code at 7.7, Tabnine at 7.1, and Factory at 7.5. Relative cost stays competitive on published Amp packaging.
Use-case matrix
| Use case | Fit | Notes |
|---|---|---|
| Multi-file agentic edits + CLI | Strong | Amp is built for agentic coding. |
| Enterprise multi-repo code search + AI | Strong | Sourcegraph platform strength. |
| Individual free Cody chat forever | Weak | Free/Pro Cody discontinued in 2025. |
| Autocomplete-only seat plugin | Mixed | Peers may be simpler if you only want completions. |
Review Excerpts
Below are excerpts from public reviews. Paid reviews and pay-for-play sites such as Clutch were excluded.
“If you like Claude Code but prefer an agent that doesn't ask for review on each file edit, or miss the IDE for reviewing diffs, I'd humbly submit you try out Amp. It has both a CLI and VS Code extension.”
“Sourcegraph Amp is pretty good as well albeit lacking a lot of the polish and features of Claude Code. But I sometimes reach for it for code review in particular since it calls out to o3 via its "oracle" tool.”
“AMP also provides really important features of a harness that others haven't quite caught up on.”
“Cody Free and Pro are gone. If you expected a cheap self-serve chat seat, you are now on Amp credits or an Enterprise conversation.”
“I have been evaluating other tools like Amp (from Sourcegraph) ... for agentic coding workflows beside Claude Code.”
Methodology
This page is an independent evaluation of Sourcegraph for buyers comparing options in coding agents & developer tools. AI Industry Reviews accepts no sponsorships, advertising, or pay-for-placement fees. Sourcegraph did not pay for this review.
What we scored
The headline number is an Overall Score on a 0-10 scale. Eight criteria fall under it in two groups.
- Buyer outcomes (for coding agents & developer tools)
- Agentic coding (Amp)
- Large-repo context / code intel
- Editor & CLI experience
- Self-serve Cody continuity
- Company & commercial
- Innovation & product leadership
- Project management & communication
- Pricing
- Contract fairness
Pricing measures whether the price looks fair for the value delivered, including packaging and renewal friction that show up in real buying cycles.
Score Composition
| Input | Weight | What it covers |
|---|---|---|
| Reviews | 40% | A proprietary read of what practitioners say about likes, complaints, and day-to-day use, including public review sites, forums, and private chat rooms. Paid reviews and pay-for-play sites such as Clutch are out of scope. |
| Product | 35% | Hands-on look at screens and workflows. |
| Pricing | 15% | Whether the price looks fair for what you get. |
| Docs & training | 10% | Docs, tutorials, and training material. |
How we balanced the evidence
The Overall Score is the simple average of the eight criteria. Recommendation language follows that score and the fit pattern described above.
Scope
Sourcegraph is graded here as coding agents & developer tools. Criteria scores can move as more review volume and product checks are added.