Get This Tool
EGC
Pricing
- Model
- Free
Summary
Every time you context-switch between AI coding sessions — or return to a project after two weeks — you spend the first twenty minutes re-explaining what you were doing, why, and what you decided last time. EGC exists to eliminate that tax.
EGC is a local-first MCP runtime that persists memory across sessions and across AI tools, so agents pick up exactly where the last session stopped. The repo structure shows explicit support for Cursor, Codex, Gemini, Kiro, Trae, and OpenCode, meaning the memory layer sits beneath whichever assistant you switch to. The system tracks completed tasks, failures, and next steps automatically — you do not write the handoff notes. The wall appears when you need a hosted or API-accessible version: the vendor describes no hosted runtime, no remote API, and no paid tier, so teams requiring cloud-accessible memory or multi-user session state have nowhere to go within this tool.
Bottom line: EGC earns its place in a solo developer's local stack for long-running projects — it breaks the moment your team needs shared, cloud-accessible session memory or a REST API another service can query.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Zero-prompt memory restoration on session start, which means developers stop spending the first part of every session re-explaining project state to an agent that forgot everything.
- Single memory layer spanning multiple AI coding assistants — Cursor, Codex, Gemini, Kiro, Trae, and OpenCode are all covered — so switching tools mid-project does not fragment your context into incompatible silos.
- Automatic tracking of completed tasks, failures, and next steps, which means the handoff document you never wrote still exists when you return after two weeks away.
- MIT license with a local-first runtime and self-hosted option, so your project memory never touches an external server and the tool cannot be deprecated behind a paywall.
- Install scripts and pre-built agent configuration files ship with the repo, which means the integration surface for supported tools is a config file change rather than a custom integration build.
Cons
Sign in to edit- No hosted runtime and no API surface: any workflow that requires memory to be accessible from a remote server, a CI pipeline, or a second developer's machine has no path forward inside EGC. Teams needing shared or cloud-accessible session state have to build their own persistence layer or switch to a tool that offers one.
- With 17 open GitHub issues and no paid support tier, production bugs in edge cases — unsupported assistant versions, memory corruption on interrupted sessions, schema mismatches after updates — land entirely on the team to diagnose and fix. Teams that cannot absorb that maintenance overhead typically move to a commercially supported memory layer.
- Coverage is limited to the AI coding assistants explicitly wired into the repo. If your tool of choice lacks a configuration directory in the project, memory persistence does not apply to it, and adding support requires contributing to the project or maintaining a fork.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Local / desktop
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-06-23T20:34:59.988Z
Best For
Who it's for
- Developers using multiple AI coding assistants
- Long-running projects needing session continuity
- Users wanting zero-prompt memory restoration
What it does well
- Resume work on a project after weeks away without re-explaining context
- Maintain consistent preferences and coding style across multiple AI tools
- Track completed tasks, failures and next steps automatically
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare EGC
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is EGC free?
- Yes — EGC is fully free to use. There is no paid tier.
- Is EGC open source?
- Yes. EGC is open source.
- Can I self-host EGC?
- Yes. EGC supports self-hosting on your own infrastructure.
- What platforms does EGC support?
- EGC is available on: Local / desktop.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Context loss between AI coding sessions is not a minor friction — it is a silent productivity drain that compounds across weeks. EGC addresses this by running a local MCP runtime that writes structured memory after each session: what was attempted, what succeeded, what failed, and what comes next. On the next session, the agent reads that memory automatically, so no re-briefing is required. The repository ships with install scripts and configuration files pre-wired for multiple AI coding assistants.
The differentiating move here is breadth of assistant coverage from a single memory layer. The repo contains dedicated configuration directories for Cursor, Codex, Gemini, Kira, Trae, OpenCode, and Codex-plugin, among others. That means a developer who uses Cursor in the morning and a different assistant in the afternoon draws from the same memory store — preference consistency and coding style travel with the context, not with the tool.
EGC fits a solo developer or small team running long projects locally, where session continuity across days and tools is the bottleneck. It does not fit teams that need shared memory across multiple developers, a hosted runtime, or a REST API that a CI pipeline or external service can call. The GitHub issue tracker lists 17 open issues as of the repo snapshot, which signals an early-stage project where production edge cases surface regularly. Teams hitting those edges are currently on their own.