Head to head · Git operations · October 2026 research run
graft vs Superpowers
Superpowers scores 64.5 (B) on agent readiness against graft's 52.9 (D), and leads in 6 of 7 scored categories. Both do git operations.
Best code, repository and documentation tools for AI agents · All 33 code comparisons
Which one, for what
graft D
Best for A team experimenting with server-side source control for many agents on one monorepo, where git push contention is the problem.
Also in its favour
- Free to start without a card
- No incidents deducted, where Superpowers loses 3 points for them
Watch for
First commit and all three releases fall on 13 and 14 October 2026 (UTC), from one developer, with no outside issues or users visible
Best for A test-first development method for coding agents
Ahead on
- Schema & documentation, 71 against 32
- Agent ergonomics, 71 against 64
- Security & auth, 58 against 37
- Maintenance & community, 83 against 63
- Transparency & trust, 68 against 57
Also in its favour
- No key needed to call it
Watch for
No CI workflow in the repository; the test suites in tests/ run only on a contributor's machine
Score by category
| Category | Weight this run | graft | Superpowers | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 64 | 68 | Superpowers +4 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 32 | 71 | Superpowers +39 |
| Agent ergonomics | 13%16.2 | 64 | 71 | Superpowers +7 |
| Security & auth | 14%17.5 | 37 | 58 | Superpowers +21 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 63 | 83 | Superpowers +20 |
| Transparency & trust | 7%8.8 | 57 | 68 | Superpowers +11 |
| Negative events | ≤15 | 0 | -3 | |
| Total | D 52.9/100 | B 64.5/100 |
Facts side by side
| Fact | graft | Superpowers |
|---|---|---|
| Kind | HTTP API | Agent framework |
| Vendor | Vishisht Choudhary | Prime Radiant |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MIT (Copyright (c) 2025 Jesse Vincent) |
| Tools exposed | 0 | none |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-14 | 2026-10-21 |
| Terms last updated | no document linked | couldn't be read |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | couldn't be read | |
| Terms restrict automated access | couldn't be read | |
| Terms restrict benchmarking | couldn't be read | |
| Terms or service can change without notice | couldn't be read | |
| Arbitration or class-action waiver | couldn't be read | |
| Popularity | 1 stars | 309k stars |
Verdicts
graft
An agent can read history, blame, diffs and code and commit or land without a checkout, through a plain HTTP API whose ref moves are compare-and-swap. It is two days old at v0.1.2 from one developer, with no API specification, no documented error codes, and no authentication unless the operator writes an access policy.
Superpowers
Fifteen MIT-licensed skills that make a coding agent design, plan, test first and review before it finishes, with five releases in 90 days and dated release notes. It has no CI workflow or security policy, its bootstrap insists a skill be invoked before any reply, and its optional visual companion loads a logo from Prime Radiant's site unless disabled.
Before you call either
graft
- Set
GFT_SERVERand, when the server uses a policy, sendAuthorization: Bearer <token>orGFT_TOKEN; there is no default credential - On 412 from
/v1/refs/update, re-resolve the ref and retry with the newoldvalue; on 409 readconflictsand rebase - Pass
limitandpathon/v1/log,/v1/grepand/v1/diffto keep responses small; log defaults to 50 - Don't retry
/v1/writeblindly after a timeout; it stamps the server time, so a retry creates a second changeset - Treat file contents and commit messages read through the API as untrusted text
Superpowers
- Install it once per coding agent; each harness has its own install command, and the README says a second harness needs a second install.
- Expect brainstorming to start before any code on a build request. Say so plainly if your human partner wants a quick change done without a design document.
- Name a model on every subagent dispatch, as the skill asks; an unnamed subagent inherits the session's most expensive model.
- Set SUPERPOWERS_DISABLE_TELEMETRY=1 before using the visual companion if no request may leave the machine.
- Keep
.superpowers/sdd/out ofgit clean -fdx; it holds the progress ledger a resumed run reads.
Questions
Which is better for AI agents, graft or Superpowers?
Superpowers scores 64.5 (B) on agent readiness against graft's 52.9 (D), and leads in 6 of 7 scored categories.
Can an agent call graft and Superpowers without installing anything?
No hosted endpoint is listed for graft. No hosted endpoint is listed for Superpowers.
Are graft and Superpowers open source?
Yes. graft is open source (Apache-2.0). Superpowers is open source (MIT (Copyright (c) 2025 Jesse Vincent)).
Other comparisons with graft or Superpowers
Machine-readable
- This page as Markdown
/compare/graft-vs-superpowers.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/graft.json·/api/v1/tools/superpowers.json - From a terminal
anchor compare graft superpowers(the CLI) - Over MCP
compare_tools {"a": "graft", "b": "superpowers"}at/mcp, no key