ByHeather MacAvelia·Last verified Jun 20, 2026

Mainline

Name: Mainline
Author: Mainline

On Our Radar

by Mainline

✓ Verified

Visit mainline.sh →

Git-native memory layer for AI coding agents. Surfaces abandoned approaches, superseded decisions, and reviewer constraints before agents edit code. Free open source; Team tier planned.

From

Custom

free ↗

GitHub

⭐ 164

View on GitHub ↗

—

Rating

MCP

Compatible

Mainline is a Git-native memory layer that gives AI coding agents access to the engineering intent behind a codebase before they make changes. Rather than letting agents infer why code exists from source alone, Mainline records decisions, abandoned approaches, superseded implementations, reviewer constraints, and explicit risks in a local Git-backed store that travels with the repository via custom refs and notes. Agents using Cursor, Claude Code, or Codex read Mainline context via hooks that auto-inject the current intent snapshot at every session start, requiring no manual retrieval step from the developer. The CLI provides start, append, and seal commands for recording intent. Setup is minimal: mainline init configures the repo in a single command, installs hooks for supported agents, and is fully operational in under 5 minutes. Pricing is open source and free for the core CLI and protocol under Apache-2.0. Team Cloud (planned, not yet released) will add hosted PR intent summaries, related prior decisions, open risks and anti-patterns, team search over repo memory, and review guardrails for AI-generated changes. Enterprise (planned) will add self-hosted or dedicated deployment, SCM and CI integration, policy controls, audit exports, and support for internal coding agents. No team or enterprise pricing has been published. The GitHub repository (mainline-org/mainline) has 147 stars as of June 2026. MCP is not supported. All data lives in your own Git remote via custom refs and notes, never in a third-party cloud. Mainline is a context and memory layer, not a coding agent. Teams expecting AI-driven code generation must pair it with a separate coding agent such as Cursor, Claude Code, or Codex.

Pricing

free

View pricing ↗

Segment

b2b

Setup

easy

Verified

Jun 20, 2026

Transparency

Public

Contract

Month-to-month

Data training

Not Trained

Autonomy

Human Optional

Capabilities

agentic-codingautonomousgit-native

Pros & Limitations

Editorial assessment

Pros

✓Git-native storage means repo memory travels with the codebase through normal Git fetch and push: no vendor lock-in, no third-party cloud dependency, and no additional infrastructure beyond existing Git workflows.
✓Hooks auto-inject intent context at every Cursor, Claude Code, and Codex session start: agents see abandoned paths and superseded decisions before making changes, eliminating the manual step of providing historical context.
✓Apache-2.0 open source core is free for all developers with the full CLI, agent protocol, and intent record format available without a paid tier or account requirement.

Limitations

⚠Team collaboration features (shared Hub, hosted intent sync, PR review integration, policy controls) are not yet released: the current product is a solo and early-team CLI only, limiting utility for larger engineering organizations.
⚠Not a coding agent: Mainline is a context and memory layer that must be paired with a separate coding agent such as Cursor or Claude Code; teams expecting AI-driven code generation will not find that here.
⚠Very early product with 147 GitHub stars and no G2 reviews: teams evaluating long-term infrastructure tools carry meaningful adoption risk compared to established alternatives with larger communities.

Technical Details

Deployment

cliself-hosted

Avg setup time5 minutes

Autonomous ratePartially automated via hooks: Mainline auto-injects intent context and runs conflict detection at session start; intent recording (start, append, seal commands) requires explicit agent or human initiation through the CLI

Integrations

CursorClaude CodeGitHub CopilotCodexGit