An open-source evaluation platform for testing AI coding agents on real-world software engineering tasks. SWE-bench Pro Runner provides 742 curated tasks across 11 production repositories, with full orchestration tooling to launch evaluations, track results, and generate analytics reports.
active 2026-03-03 → 2026-05-01 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 60 days from 2026-03-03 to 2026-05-01. Pushes: 19 total, peak 7 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 29 total, peak 24 in a day. Comments: 8 total, peak 4 in a day. Stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| manojvas | 56 | 19 | 0 | 8 |
Recent activity
Latest issues, pull requests and releases
- Issue#37manojvas2026-03-22 22:43[TEST] E2E validation of Cursor CLI pipeline
- Issue comment#37manojvas2026-03-22 22:43[TEST] E2E validation of Cursor CLI pipeline
- Issue#35manojvas2026-03-22 22:43[FEAT] Update orchestration scripts for cursor agent
- Issue comment#35manojvas2026-03-22 22:43[FEAT] Update orchestration scripts for cursor agent
- Issue#33manojvas2026-03-22 22:43[FEAT] Add cursor agent support to swebench-eval.yml workflow
- Issue#32manojvas2026-03-22 22:42[FEAT] Create run_cursor.py wrapper scripts for all 11 repos
- Issue comment#32manojvas2026-03-22 22:42[FEAT] Create run_cursor.py wrapper scripts for all 11 repos
- Issue#31manojvas2026-03-22 22:42[FEAT] Add Cursor CLI to Docker images
- Issue comment#31manojvas2026-03-22 22:42[FEAT] Add Cursor CLI to Docker images
- Issue#23manojvas2026-03-03 20:45ADR-008: Create Docker image manifest with variant rationale
- Issue#28manojvas2026-03-03 20:44ADR-013: Evaluate sidecar pattern for agent CLI containers
- Issue#28manojvas2026-03-03 20:44ADR-013: Evaluate sidecar pattern for agent CLI containers
- Issue#27manojvas2026-03-03 19:32ADR-012: Evaluate MCP support for Codex and Gemini agents
- Issue#25manojvas2026-03-03 19:31ADR-010: Document hybrid Docker build strategy (prebaked image + runtime setup.sh)
- Issue#25manojvas2026-03-03 19:31ADR-010: Document hybrid Docker build strategy (prebaked image + runtime setup.sh)
- Issue#21manojvas2026-03-03 19:30ADR-006: MAX_TURNS workflow input is accepted but never used by agent wrappers
- Issue#21manojvas2026-03-03 19:30ADR-006: MAX_TURNS workflow input is accepted but never used by agent wrappers
- Issue#18manojvas2026-03-03 19:29ADR-003: token_secret_name in config.yaml is parsed but unused
- Issue#17manojvas2026-03-03 19:29ADR-002: MCP server name hardcoded as 'mcp-server' — make configurable
- Issue#17manojvas2026-03-03 19:29ADR-002: MCP server name hardcoded as 'mcp-server' — make configurable
- Issue comment#14manojvas2026-03-03 19:11ARCHITECTURE.md and README.md missing new workflows and inputs
- Issue#14manojvas2026-03-03 19:10ARCHITECTURE.md and README.md missing new workflows and inputs
- Issue#12manojvas2026-03-03 19:10Fix task counts: 742 → 731 across all documentation
- Issue comment#11manojvas2026-03-03 18:53Consolidate and add Docker image build workflow
- Issue comment#2manojvas2026-03-03 18:39Add --max-turns to agent CLI invocations
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.