Activity
Contributors
README
Blast Radius
What does a vulnerable dependency put at risk, in business terms, and can an agent fix it safely? Team Redemption (solo) · neatHack 2026 · built with neatlogs, Entire and cfo.ai
When a package is vulnerable, the people who decide what to do (product, finance, support, security) don't see packages. They need what breaks, who owns it, what it costs, by when. Blast Radius maps code → packages → features → revenue and owner, then an agent upgrades the packages, patches code that breaks, runs the tests, and re-checks with an independent scan.
- Demo video: posted on X with the submission (source: video/)
- Progress thread: https://x.com/axhat_/status/2108951386805387510
- Live dashboard (AWS us-east-1): http://100.31.116.240/ (read-only) · onboarding: http://100.31.116.240/onboard · the box re-pulls this repo every 5 minutes (
deploy/user-data.sh) - Write-up: WRITEUP.md · Build log: hackathon.md
Results (honest numbers)
Same task, 3 runs each, tests pass 3/3 on both (cost is our estimate from token counts, not billing):
| Naive agent | Improved agent | Change | |
|---|---|---|---|
| LLM steps | 19.7 | 4.3 | -78% |
| Tool calls | 36.3 | 5.3 | -85% |
| Est. cost / run | $0.199 | $0.041 | -79% |
| Time | 48.4s | 18.5s | -62% |
On 4 real open-source repos (rewound to just before maintainers merged a Dependabot fix) the agent matched or beat the human fix and tests still passed. Only 6 of 51 old repos could even be rebuilt, which is a finding in itself. Details and limits: OSS_REPLAY.md.
How the three required tools are used
| Tool | In the product | In building it | Evidence |
|---|---|---|---|
| neatlogs | Audit trail of every fix (what the agent read, changed, spent) | The first trace exposed wasted re-reads; fixing it gave the table above. Also holds a real failed-action → recovery trace | hackathon.md (trace IDs), social/media/*trace*.jpg |
| Entire | Graph finds the files and covering test for a package (agent --mode entire). Checkpoints tie each commit to the session that made it | Every commit has a checkpoint | Checkpoint · ID 01M4JYYTA9J94PDTA97JDYS36X |
| cfo.ai | Pricing and runway from the measured cost per fix | Showed why the cost cut matters at real-repo scale | docs/cfo-plan.md, social/media/cfo-*.jpg |
Run it
cp .env.example .env # LITELLM_API_KEY, NEATLOGS_API_KEY (agent only); the dashboard needs no keys
uv venv && uv pip install -r requirements.txt
.venv/bin/uvicorn web.app:app --port 8765 # dashboard at /, onboarding at /onboard
demo/shop/scripts/reset.sh # fresh seeded demo shop (vulnerable pins)
.venv/bin/python -m agent.run --label try --mode entire # fix it (naive | improved | entire)
.venv/bin/python -m oss.replay data/oss_candidates.json Snehasis5/ci-cd-demo # replay a real repo
The agent runner uses a shared, budgeted model key, so it is not deployed publicly; the deployed dashboard is read-only.
Layout
agent/ scan (OSV), graph, fixer loop, tools · web/ dashboard + onboarding · oss/ real-repo replay · demo/shop/ seeded app · video/ Remotion demo · data/runs/ raw run results · docs/ plans
Limitations
Demo business data is hand-written (business.yaml); real onboarding asks the buyer to confirm it. Python requirements.txt only. Small samples (n=3 per agent, 4 real repos, some with a single test). Costs are estimates. Onboarding is a prototype with no sign-up or billing.
