Sourcegraph Problems & Issues
SaasCode AI platform for devs and engineering teams
Best-in-class code search but expensive, unstable company direction, and individual plans discontinued. Only recommended for enterprises where code discovery is critical pain point.
Should you use Sourcegraph?
Try with cautionSourcegraph works for some teams, but users report recurring problems (score 55/100). Most reported issues: Cody Pro discontinued July 2025; Enterprise pricing very expensive; Company instability - multiple layoffs. Not a good fit for: Individual developers (non-enterprise); Budget-conscious organizations; Organizations seeking vendor stability. Users most often switch to Cursor, GitLab, OpenGrok.
Top problems
- Cody Pro discontinued July 2025
- Enterprise pricing very expensive
- Company instability - multiple layoffs
Good for
- Large enterprises with big codebases
- Teams needing code search specifically
- Enterprises already using Cody Enterprise
Avoid if you are
- Individual developers (non-enterprise)
- Budget-conscious organizations
- Organizations seeking vendor stability
Common alternatives: Cursor, GitLab, OpenGrok
Overview
Sourcegraph is a code search and AI assistant platform for enterprise development teams. Features code search across repositories, Cody AI assistant (being deprecated for Amp), and codebase understanding. Founded in 2013, went through layoffs in 2025.
Signals & Issues
Patterns extracted from real user feedback — not raw reviews.
Like all LLM-based tools, Cody experiences occasional hallucinations. Generated code may look correct but contain subtle bugs. Requires careful human oversight and validation. Not fully trustworthy for critical code paths.
Individual users must migrate from Cody to Amp - new product with different pricing and features. Transition credits provided but workflow disruption significant. Enterprise customers unaffected but product direction feels unstable.
Cody struggles with complex, multi-step logic and long dependency chains. Experiences occasional hallucinations requiring human oversight. Context windows are finite - large repositories require iterative prompting for accuracy. Not suitable for fully autonomous complex tasks.
For newer developers, Cody can become a crutch if outputs aren't validated. AI-generated code without understanding is a risk. Reviews warn against dependency on AI for learning - fundamentals may be skipped.
Cody Free, Cody Pro, and Cody in Starter plans were deprecated July 23, 2025. Individual users forced to migrate to Amp (new product) or find alternatives. $10-40 in transition credits offered but product direction unclear. Major disruption for existing users.
Enterprise tier costs $59/user/month - one of the most expensive AI coding tools. For 100 developers, that's $70,800/year. Starter at $19/user/month limited to 50 users. Volume discounts require sales negotiation. Cost prohibitive for many teams.
In certain situations, pricing is based on combination of active users AND lines of code indexed. Large monorepos may face higher costs than expected from per-seat pricing alone. Requires sales conversation to understand true costs.
Sourcegraph experienced multiple layoffs in 2025, including 8% workforce reduction (24 employees) and multiple marketing team cuts within 6 months. Company went from growth to survival mode. Employee reviews describe leadership as 'toxic' and product as 'directionless.'
User reported being banned for accidentally creating a second account by logging in with GitHub after paying subscription. Also experienced 429 rate limiting on paid account. When contacting support as recommended, account was banned for 'Acceptable Use Policy' violation. Heavy-handed enforcement.
Product direction clearly favors enterprise customers. Individual plans discontinued. Free/Pro users pushed to new Amp product. Company explicitly 'simplifying offerings to better serve customers' - meaning enterprise, not individuals.
Customer reviews indicate Sourcegraph was seen as a 'vitamin' (nice-to-have) rather than 'painkiller' (essential). Hard to justify ROI to management. Code search valuable but not critical enough to survive budget cuts at many organizations.
Context windows limit how much code Cody can understand at once. Extremely large or tangled repositories may require multiple prompts to get accurate results. Not as seamless as marketing suggests for enterprise-scale codebases.
What Users Love
Industry-leading code search across repositories
Search across all your repositories simultaneously with powerful regex and structural search. Find code patterns, understand dependencies, and navigate large codebases efficiently. Core strength since company founding.
Strong repository context understanding
AI understands your specific codebase, not just general patterns. Can explain code, summarize PRs, and generate boilerplate that fits your project. Better contextual awareness than many competitors.
Fast on straightforward coding tasks
Quick at boilerplate generation, simple refactoring, and code explanations. Speeds up repetitive tasks significantly. Good for day-to-day coding acceleration.
Helpful PR summaries and documentation
Can generate PR descriptions, code documentation, and technical summaries. Useful for teams needing consistent documentation practices. Reduces documentation burden.
Enterprise-grade security features
Enterprise tier includes SSO, audit logs, and enterprise security controls. Designed for large organizations with compliance requirements. Takes security seriously.
Integrates with existing development workflows
Works with VS Code, JetBrains IDEs, and browser extensions. Integrates with GitHub, GitLab, Bitbucket. Fits into existing enterprise development infrastructure.
Pricing Plans
Users: Individual
Limitations: DISCONTINUED - migrate to Amp or find alternative
Users: Up to 50 users
Limitations: 50 user limit, fewer enterprise features than full Enterprise tier
Users: Unlimited
Limitations: Very expensive, pricing may include LOC component, requires sales process
Users: Individual
Limitations: New product, unknown long-term pricing, replaces discontinued Cody individual plans
Features
Core
- Code search across repositories
Core strength - industry leading
AI
- AI code completion (Cody)
Enterprise only - individual plans discontinued
- Codebase context understanding
Good contextual awareness
- PR summaries
Useful documentation feature
- Agentic workflows (Amp)
New product - replaces Cody individual
Integrations
- VS Code extension
Available
- JetBrains extension
Available
- Browser extension
For code search
- GitHub/GitLab integration
Repository connections
Security
- Enterprise SSO
Enterprise tier
- Audit logs
Enterprise tier
Pricing
- Free tier
Discontinued July 2025
Editing
- Multi-file editing
Limited compared to Cursor
Deployment
- On-premises deployment
Self-hosted option available
Who Should Use This?
Good Fit
Large enterprises with big codebases
Code search across repositories is genuinely useful at scale. Enterprise security features meet compliance needs. Worth $59/user if code discovery is a real pain point. Core value proposition strongest here.
Teams needing code search specifically
No one does code search better than Sourcegraph. If finding code across repositories is your primary pain, this is the tool. AI features are secondary to search capabilities.
Enterprises already using Cody Enterprise
Cody Enterprise plans unaffected by individual plan discontinuation. Continued investment promised. If already deployed, no immediate migration needed.
Neutral
Small teams under 50 developers
Enterprise Starter at $19/user is competitive but capped at 50 users. Worth considering if code search is critical need. However, simpler alternatives like Copilot may suffice.
Avoid
Individual developers (non-enterprise)
Cody Free and Pro discontinued July 2025. Must use new Amp product with unclear pricing. Company clearly deprioritizing individual users. Use Codeium, Copilot, or Cursor instead.
Budget-conscious organizations
At $59/user enterprise pricing, Sourcegraph is among the most expensive options. Copilot Business ($19/user) or Cursor ($40/user) offer similar AI features at lower cost. Hard ROI justification.
Organizations seeking vendor stability
Multiple layoffs in 2025, product line discontinuation (Cody), and direction changes suggest instability. Employee reviews mention 'directionless' product. Consider more stable vendors.
Developers wanting AI code completion
AI capabilities are secondary to code search. Cody/Amp not as polished as Copilot or Cursor for pure AI assistance. Better options exist for AI-first workflows.
Regret Patterns
Common buyer's remorse scenarios reported by users.
Paid for Cody Pro expecting continued AI assistance. Product discontinued July 2025 with migration to Amp required. Transition credits insufficient for long-term use. Had to find new tool and rebuild workflow.
Evaluated Sourcegraph for team assuming reasonable pricing. Discovered $59/user/month - 3x Copilot. 100 developers = $70k/year. Could not justify ROI to management. Had to choose cheaper alternative.
Deployed Sourcegraph for enterprise code search. News of layoffs, product discontinuation, and negative employee reviews raised red flags. Management questioned long-term vendor viability. Considering migration despite sunk costs.
Implemented Sourcegraph for code search benefits. During budget review, product categorized as 'vitamin not painkiller.' Hard to prove direct ROI. Lost tool during cost-cutting despite team finding it useful.
Created second account accidentally by logging in with GitHub after paying subscription. Account banned for 'Acceptable Use Policy' violation. Support unhelpful. Lost paid subscription and access.
Expected Cody to handle complex enterprise codebase seamlessly. Found context window limitations, hallucinations, and need for iterative prompting on large repos. Marketing overpromised actual capabilities.
When It Breaks Down
Scenarios where this product tends to fail users.
Cody Free and Pro ended July 2025. Individual users must migrate to Amp or find alternatives. No direct replacement offered. Workflow disruption for all non-enterprise users.
At $59/user/month, Sourcegraph is hard to justify in cost-conscious environments. Seen as 'vitamin' not 'painkiller.' Often first to be cut when budgets tighten.
Enterprise Starter capped at 50 users. Growing team must upgrade to full Enterprise at $59/user - sudden cost jump. No intermediate tier available.
Layoffs and product discontinuation raise questions about company future. Enterprise customers face vendor risk assessment. May choose more stable alternatives at renewal.
Extremely large or complex codebases require iterative prompting for accuracy. Context windows limit AI effectiveness. Not as seamless as marketing suggests for massive monorepos.
Generated code contains subtle bugs from AI hallucinations. Without proper review, bugs reach production. Requires establishing new validation processes for AI-generated code.
Alternatives Users Switch To
GitHub Copilot
8x mentionedTeams switch for better AI code completion at lower cost ($19 business vs $59 enterprise). Copilot more polished for AI-first workflows. Trade-off: Weaker code search capabilities than Sourcegraph.
Cursor
6x mentionedDevelopers switch for superior multi-file editing (Composer) and codebase indexing. Better AI capabilities for complex tasks. Trade-off: No enterprise code search, VS Code only.
GitLab
5x mentionedTeams switch for all-in-one DevOps with built-in code search. Complete CI/CD platform. Trade-off: Code search less powerful than Sourcegraph, different focus.
OpenGrok
4x mentionedBudget-conscious teams switch for free, self-hosted code search. Oracle-backed open source. Trade-off: No AI features, requires infrastructure management.
Tabnine
4x mentionedEnterprises switch for on-premises AI deployment with air-gapped option. Trade-off: Weaker code search, AI capabilities lag behind Copilot/Cursor, expensive ($39/user).
Frequently Asked Questions
See how Sourcegraph compares in our Best AI Coding Software rankings, or calculate costs with our Budget Calculator.
Work at Sourcegraph or spotted something outdated? Suggest a correction — we verify every change against public sources. See our methodology.