eve-software-factory-template vs personal-agent-template
Two of the top agent backends, side by side: score, setup, license, activity and what each review found.
eve-software-factory-template
eve pipeline that turns GitHub or Linear issues into reviewed draft PRs
personal-agent-template
eve and Nuxt personal agent with Slack, GitHub, Linear and per-user memory
| What we compare | eve-software-factory-template | personal-agent-template |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 46, known | 30, niche |
| Freshness | 100, active | 100, active |
| Maintenance | 35, patchy | 11, weak |
| Easy to run | 67, easy | 67, easy |
| Agent-ready | 70, partly | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 1.2k | 476 |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Sep 2026 | Sep 2026 |
| Last release | None published | None published |
| Language | TypeScript | TypeScript |
| Docker | No | No |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Not stated | Not stated |
eve-software-factory-template
An eve pipeline named Foreman: label an issue factory, @mention it, or delegate from Linear, and four agents (classifier, analyst, implementer, reviewer) each run in their own sandbox and end with a draft pull request on FACTORY_REPO. The reviewer sees only the pushed branch, a factory brain keeps notes about your repo between runs, and it deploys to Vercel with GitHub and Linear connectors. For teams piloting agent-written PRs with human merge.
Who it is for: Teams piloting agent-written pull requests with human merge
Strengths
- Reviewer is isolated from the implementer; verdicts are made against the real diff
- Six entry points including red-CI self-repair on factory branches only
- Local dev TUI treats runs as untrusted; GitHub writes wait for approval
- Separate docs site; CLAUDE.md and AGENTS.md included
Weaknesses
- Tied to eve, Vercel Connect, Vercel Sandbox and Vercel Blob
- No model provider named in the README; model access comes through the Vercel stack
- No tests listed
- First task fails if the GitHub App cannot reach FACTORY_REPO; the error surfaces late
- TypeScript, eve, ai-sdk
- Needs vercel, github-app-connector, linear-connector, vercel-blob
- GitHub template
- env example file
personal-agent-template
A Nuxt app plus an eve agent runtime: Better Auth email login, web chat with threads that eve persists, Slack DMs and mentions linked to the same user, GitHub tools with durable approval on writes, Linear via Vercel Connect MCP, and a bounded per-user memory document in Vercel Blob. Postgres via Drizzle holds users and links; on Vercel it deploys as two services. For developers building a single-user or small-team assistant on eve.
Who it is for: Developers building a personal or small-team assistant on eve
Strengths
- Memory is per authenticated principal, recalled before every turn and after compaction
- Slack identity links to the web profile so context follows the user
- Write actions on GitHub gate on durable approvals
- CI workflow, CLAUDE.md and AGENTS.md present
Weaknesses
- Needs Vercel Connect for Slack and Linear; self-hosting those integrations is on you
- No model provider named in the README; configured through eve
- No tests listed; CI covers typecheck and build
- Requires Node 24+
- TypeScript, eve, ai-sdk
- Needs postgres, vercel-blob, vercel-connect
- GitHub template
- env example file
- sign-in: Better Auth