Logo AnoveLogo AnoveExplAIn
CartesPionniers de l'IA
Retour au répertoire

Coder Agents (self-hosted AI coding agent)

par Coder

AI Application
Faible confiance

Coder Agents is a native AI coding agent built into the self-hosted Coder platform. The entire agent loop runs in the customer's Coder control plane: it provisions workspaces on demand, works against models the customer approves (Anthropic, OpenAI, Google, AWS Bedrock or self-hosted endpoints), can be triggered from chat or an API for CI, GitHub Actions, Slack and Jira, and uses centrally managed MCP tools and skills. Controls described by the vendor include model governance, per-user and per-group spend limits, no LLM API keys in workspaces, SSO identity on every action, workspace-template restrictions and usage analytics including pull-request and merge rates. Rated high: an agent that writes and changes code and runs commands in environments with access to source code and cloud credentials is a high-impact system, and its safety rests largely on customer configuration, since Coder's docs say self-hosting alone does not make a deployment compliant. The risk is raised by Coder's own recent incident: on 31 Aug 2026 its module registry (registry.coder.com), which provisions workspaces and installs AI coding agents, served tampered Terraform modules for about 14 hours that stole cloud, CI/CD, SSH, OIDC, AI-provider and MCP credentials (advisory GHSA-vx42-ghc9-gw65, CVSS 9.0); third-party reports say Coder cannot enumerate which deployments pulled them. Coder says it found no indication that customer data it holds was affected, and engaged Coalition Incident Response for an independent review whose summary was due 30 Sept. Because the product is self-hosted, prompts and code go to the LLM providers the customer configures, not to Coder; Coder's trust center lists SOC 2 Type 2 behind an access request but its AI section is a one-line statement with no AI policy, and no published safety or failure-rate data for the agent was found. The rating could be lowered if the independent review, SOC 2 scope and agent guardrails check out and customers mirror or pin the registry.

Visiter le site web

Score de transparence

Pondéré sur quatre piliers · mis à jour le October 27, 2026

Note globale
29% pondéré
ABCDF
Modèle
—
Pas encore évalué
Infrastructure
—
Pas encore évalué

Capacités

Autonomous Code Generation And Modification
Agent Task Execution In Workspaces
Automatic Workspace Provisioning
Agent Triggering Via Api Ci Slack And Jira
Mcp And Skills Extension
Usage And Pr Outcome Analytics

Informations sur le fournisseur

Informations complètes sur le fournisseur/prestataire de cette application IA

CoderVoir tous les produits →
Coder Technologies, Inc.(Exerçant sous le nom : Coder)
Informations de contact
coder.com/
ask@coder.com
+1 512-593-8418
Adresse enregistrée
9901 Brodie Lane, Ste 160 #1212, Austin, TX, 78748, US

Informations fournisseur (Règlement IA de l’UE)

Statut de vérification:
Partially Verified
(Dernière vérification : October 27, 2026)
Coder Technologies, Inc.(Exerçant sous le nom : Coder)
9901 Brodie Lane, Ste 160 #1212, Austin, TX, 78748, US
ask@coder.com+1 512-593-8418
Coder posts incident and advisory updates on its Trust Center and in GitHub security advisories, and says it will use the Trust Center for sub-processor, vulnerability and incident updates. It publishes a changelog, runs a public vulnerability disclosure policy (updated April 2025) with 90-day coordination and discretionary bounties, and engaged an independent firm (Coalition Incident Response) to review its handling of the August 2026 registry incident. Self-hosted customers get audit events exportable to their SIEM.
The Terms cover the website only (as-is, US$100 liability cap, intended for US visitors), and the commercial subscription terms, DPA and any AI terms were not public. The Privacy Policy was last reviewed in October 2024 and does not mention Coder Agents or the AI Gateway. Coder's own docs say self-hosting alone does not make a deployment compliant, since that depends on how the customer configures and runs Coder. No accuracy, safety-evaluation or failure-rate information is published for Coder Agents, and the Trust Center's AI section is a one-line statement.

Risques potentiels

1 points d'attention identifiés

1

Révision recommandée avant utilisation

Ces points d'attention sont automatiquement identifiés sur la base d'informations publiquement disponibles sur le fournisseur et les données du catalogue IA. Les risques réels peuvent varier selon votre cas d'usage et votre implémentation spécifiques.

Conformité et risques

Obtenez des informations sur les risques en exécutant des évaluations sur cette application IA.

Vous travaillez chez Coder ? Revendiquez cette fiche pour corriger ou compléter les données.

Ajouté : October 27, 2026
Mis à jour : October 27, 2026

Prêt à gérer vos applications IA ?

Suivez, évaluez et gouvernez vos applications IA avec Anove.

Logo AnoveLogo AnoveAnove International B.V.

Nous aidons les organisations à découvrir et gérer les applications IA de manière responsable. Votre source de confiance pour la gouvernance et la conformité IA.

Liens rapides

  • Parcourir le répertoire
  • FAQ
  • Cartes IA par secteur
  • Se connecter

Ressources

  • Documentation
  • Statut
  • Anove.ai

Conditions

  • Politique de confidentialité
  • Conditions générales
  • Divulgation responsable
  • Mention légale IA
  • Politique de sécurité

© 2026 Anove International B.V. Tous droits réservés.