Agent de développement autonome ancré dans l'ensemble de votre base de code — modifications multi-fichiers avec un contexte approfondi.
Demo · hover to playCode intelligence agent for enterprise — answers questions about your code, navigates large monorepos.
Autonomous campaign execution across email, ads, and web at brand-safe scale.
| Spec | Sourcegraph Cody | Tofu |
|---|---|---|
| Agent Rank | 77 / 100 (A) | 63 / 100 (B) |
| Autonomy | Semi-autonomous | Autonomous |
| Pricing | Freemium · from $9 | Subscription |
| Open source | No | No |
| Capabilities | Code, Tool use, RAG, Memory | Tool use, Memory, RAG |
| Integrations | 4 apps | 5 apps |
| Verified | Verified | — |
| Released | Feb 2025 | Jun 2025 |
Calculé automatiquement à partir de l'autonomie, des capacités, des intégrations, de la tarification, de la maturité et de la vérification éditoriale. Mis à jour à chaque déploiement. Comment est-ce calculé ?
Calculé automatiquement à partir de l'autonomie, des capacités, des intégrations, de la tarification, de la maturité et de la vérification éditoriale. Mis à jour à chaque déploiement. Comment est-ce calculé ?
Pick Sourcegraph Cody if cost is the main constraint or if you want a vendor we've verified for accessibility and pricing accuracy.
Try Sourcegraph Cody →Affiliate links. We may earn a commission at no extra cost to you.
Pick Sourcegraph Cody if cost is the main constraint or if you want a vendor we've verified for accessibility and pricing accuracy. Pick Tofu if you want the highest autonomy and the verification loop is in place. Most working teams running both can use Sourcegraph Cody for primary work and Tofu for the workflows where its specific strengths matter.
Sourcegraph Cody starts at Freemium · from $9; Tofu starts at Subscription. Sourcegraph Cody is the cheaper entry option. For team deployments the TCO can differ — use the AI Agent Rank TCO calculator for your specific volume.
Tofu is the more autonomous of the two (Autonomous vs Semi-autonomous). Higher autonomy ships throughput faster but requires verification loops in place — see our autonomous-vs-copilot framing for when each tier wins.
Adjacent agents in the same category with overlapping capabilities — worth a side-by-side glance before you commit.
Agent de développement autonome ancré dans l'ensemble de votre base de code — modifications multi-fichiers avec un contexte approfondi.
Demo · hover to playL'agent IA d'entreprise d'AWS — assistant de codage, chat professionnel et applications Q personnalisables ancrées dans vos données AWS.
L'assistant IA de pair-programming de GitHub — complétions inline, chat et le nouveau mode agent qui soumet des PR.