Home/Compare/self-repair vs code-review-graph

Comparison

self-repair vs code-review-graph

Verdict

Pick self-repair when tags unique to self-repair: python; pick code-review-graph when tags unique to code-review-graph: ai-coding, claude, claude-code, code-review.

Markdown twin · self-repair alternatives · code-review-graph alternatives

GraphCanon updated today

self-repair logo

self-repair

theoxo/self-repair

15pushed May 2, 2024
vs
code-review-graph logo

code-review-graph

tirth8205/code-review-graph

19kpushed Jun 14, 2026

Trust & integrity

Signalself-repaircode-review-graph
Maintenance
Archived (800d since push)
As of today · github_public_v1
Active (26d since push)
As of 1d · github_public_v1
Provenance
Not a fork · Personal account
As of today · github_public_v1
Not a fork · Personal account
As of 1d · github_public_v1
Security (OSV)
No criticals
As of today · osv@v1
No MCP manifest
As of 1d · mcp_manifest

Tagline

self-repair
[ICLR 2024]: Is Self-Repair a Silver Bullet for Code Generation?
code-review-graph
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo w

Stars

self-repair
15
code-review-graph
19k

Forks

self-repair
3
code-review-graph
2.1k

Open issues

self-repair
1
code-review-graph
185

Language

self-repair
Python
code-review-graph
Python

Adopt for

self-repair
-
code-review-graph
-

Persona

self-repair
-
code-review-graph
-

Runtime

self-repair
-
code-review-graph
-

License

self-repair
-
code-review-graph
MIT

Last pushed

self-repair
May 2, 2024
code-review-graph
Jun 14, 2026

Categories

self-repair
Evaluation & Observability
code-review-graph
Developer Tools, Evaluation & Observability, LLM Frameworks

Trust and health

Maintenance

self-repair
Archived (8%)
code-review-graph
Active (82%)

Days since push

self-repair
800d
code-review-graph
26d

Archived on GitHub

self-repair
Yes
code-review-graph
No

Open issues (now)

self-repair
1
code-review-graph
185

Security scan

self-repair
No criticals
code-review-graph
No MCP manifest

Full report

self-repair
Trust report
code-review-graph
Trust report

Choose self-repair if…

  • Tags unique to self-repair: python.
  • Leaner open-issue backlog (1).

When NOT to use self-repair

  • self-repair is archived on GitHub. Prefer an active alternative unless you maintain a private fork or need a frozen dependency.
  • Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers.

Choose code-review-graph if…

  • Tags unique to code-review-graph: ai-coding, claude, claude-code, code-review.
  • Also covers Developer Tools, LLM Frameworks.
  • More GitHub stars (19k vs 15) - visibility, not fit.

When NOT to use code-review-graph

  • Developer Tools: A gateway is overkill when you're pinned to a single provider and model.
  • Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers.
  • LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves.

Explore

Sources

Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.

GitHub stars on cards: self-repair 15 · code-review-graph 19k (synced Jul 11, 2026).

Common questions

What is the difference between self-repair and code-review-graph?
self-repair: [ICLR 2024]: Is Self-Repair a Silver Bullet for Code Generation?. code-review-graph: Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo w. See the comparison table for live GitHub stats and shared categories.
When should I choose self-repair over code-review-graph?
Choose self-repair over code-review-graph when Tags unique to self-repair: python; Leaner open-issue backlog (1).
When should I choose code-review-graph over self-repair?
Choose code-review-graph over self-repair when Tags unique to code-review-graph: ai-coding, claude, claude-code, code-review; Also covers Developer Tools, LLM Frameworks; More GitHub stars (19k vs 15) - visibility, not fit.
When should I avoid self-repair?
self-repair is archived on GitHub. Prefer an active alternative unless you maintain a private fork or need a frozen dependency. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers.
When should I avoid code-review-graph?
Developer Tools: A gateway is overkill when you're pinned to a single provider and model. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves.
Is self-repair or code-review-graph more popular on GitHub?
code-review-graph has more GitHub stars (19,416 vs 15). Stars measure visibility, not whether either tool fits your constraints.
Are self-repair and code-review-graph open source?
Yes - both are open-source projects on GitHub.
Where can I find alternatives to self-repair or code-review-graph?
GraphCanon lists graph-backed alternatives at self-repair alternatives and code-review-graph alternatives (self-repair markdown twin, code-review-graph markdown twin), ranked by typed relationship edges rather than popularity votes.
Is there a machine-readable version of this comparison?
Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
Which is better maintained, self-repair or code-review-graph?
self-repair: Archived. code-review-graph: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
Where are the full trust reports for self-repair and code-review-graph?
GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: self-repair trust report; code-review-graph trust report.