Expleo CodePle - Enterprise AI Software Engineering Platform
Expleo Group · Software Development
Certification per AWS Marketplace.
Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
Every engineering organisation feels the same drag. Context is scattered across tickets, wikis, code and databases; boilerplate and tests eat hours that should go to design; unfamiliar code slows every change; and reviews pile up while quality and security standards drift between teams. AI coding tools promise relief but usually arrive as opaque cloud services that cannot be governed, audited, or run where regulated data lives.
**CodePle, Expleo's enterprise AI software engineering platform**, closes that gap across the entire software development lifecycle, not a single step. It works where engineers already work - VS Code, JetBrains and the CLI - and moves a change through plan, design, implement, test, review, deploy and operate, with the engineer accountable at every stage. Paste a ticket and CodePle produces a task breakdown and plan; approve it and the agent implements in small, reviewable commits, adds and runs tests, fixes failures, and drafts the PR description and self-review summary.
Show the rest of the publisher’s description (26 more lines)
The platform is model-agnostic and layered for control. Choose the model per session and per mode, connecting through hosted provider APIs, a managed gateway routing to hundreds of models, or fully local LLMs for air-gapped estates - no vendor lock-in. Named modes (agents) each bundle a model, system prompt and scoped tool/permission set. Reusable Skills add on-demand instructions, and a semantic embeddings index lets the agent search large codebases by meaning, not exact text.
CodePle connects to the systems your team already relies on through the Model Context Protocol (MCP): issue trackers such as GitHub and Jira, databases, docs and wikis, observability, and internal APIs - turning tickets into plans and PRs and grounding answers in real schema, code and logs. Persistent, versioned project rules (AGENTS.md or .codeple/rules.md) enforce coding standards, architecture boundaries, testing expectations and do-not-touch paths in every session.
Built for regulated engineering in banking, financial services, insurance and the public sector, CodePle deploys self-hosted on AWS, on your own cloud VMs, or fully air-gapped on-premises. Granular permissions keep shell, network and git-push actions prompted; SSO/OIDC, secrets-vault injection and encrypted session storage protect the estate; and customer code and data never leave your environment and are never used to train models.
**Software Development Lifecycle Coverage**
- Plan - draft tickets, break down tasks and estimate; prioritisation and scope stay with the engineer
- Design - propose and compare designs, spike prototypes, draft Architecture Decision Records; architecture decisions remain human-owned
- Implement - generate, edit and refactor code in small, reviewable commits, honouring project rules and language standards
- Test - write unit, integration and edge-case tests in the team's existing style and run them until green
- Review - summarise diffs and rank bugs, security risks and missing tests by severity; approval stays human
- Deploy - draft CI/CD pipelines, infrastructure-as-code, deployment scripts and release notes; go/no-go is human
- Operate - analyse logs, draft fixes and runbooks, assist incident diagnosis
**Key Capabilities**
- Ticket-to-PR delivery inside VS Code, JetBrains or the CLI
- Agentic coding workflows - explain, implement, debug, refactor, review and document
- Model-agnostic, no lock-in - hosted APIs, managed gateway, or fully local LLMs
- MCP integrations - issue trackers, databases, docs, observability and internal APIs
- Semantic codebase indexing across medium-to-large repositories
- Versioned project rules applied automatically every session
- Governance and enterprise security - per-action permissions, cost caps, checkpoints, SSO, secrets-vault injection, air-gapped deployment
**Engagement Process**
Expleo delivers CodePle as a managed professional service with a structured engagement path:
- **Discovery and Scoping** - An initial workshop to assess your team's workflows, toolchain, security requirements and deployment topology.
- **Deployment and Configuration** - Expleo engineers deploy CodePle on your AWS environment, customer cloud VMs, or air-gapped infrastructure, configure SSO/OIDC, secrets-vault integration, project rules and MCP connections to your issue trackers and databases.
- **Enablement and Pilot** - Guided onboarding for your engineering teams, including hands-on training, workflow configuration and a monitored pilot period.
- **Handoff and Ongoing Support** - Delivery of configuration documentation, admin playbooks and transition to ongoing support.
To begin, subscribe through AWS Marketplace and Expleo's team will schedule a discovery workshop to scope your deployment.
Highlights
Highlighted by the publisher on AWS Marketplace.
One platform across the whole SDLC. CodePle takes a change from ticket to reviewed pull request - plan, implement in small commits, generate and run tests, then draft the PR and self-review - inside VS Code, JetBrains and the CLI, with the engineer accountable at every step. No stitching separate tools together per phase.
Governed by design, human in control. Granular per-action permissions keep shell, network and git-push prompted. Cost caps, git-snapshot checkpoints, versioned project rules and human review sign-off keep automated change safe, consistent and reversible. Customer code and data never leave your environment and are never used to train models.
Model-agnostic and self-hostable for regulated industries. Run against hosted providers, a managed gateway routing to hundreds of models, or fully local LLMs. Deploy self-hosted on AWS, customer cloud VMs, or fully air-gapped on-premises with SSO/OIDC, secrets-vault injection and encrypted session storage. Structured engagement from Expleo includes discovery, deployment, enablement and ongoing support.
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Sources
Linked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.