CodexCoral Code
Better work.
With your
coding agent.
We give Codex and Claude Code a network of agents responsible for your code, its connections and the work to be done.
Follow a real Q&A task from TruffleHog, a tool that finds exposed secrets in code.
Scroll to follow the investigation
Your codebase.
Hundreds of agents.
We build a network of file-level agents across your codebase. Each has its own context and responsibility for its assigned code.
File dependencies become communication paths.
On large projects, the network can grow to hundreds of agents as connected files are brought in. Each file has an owner; directional dependencies connect those owners. The network is broader than the agents working at any one moment.
Ask the owners.
Follow the evidence.
We connect your question to the agents responsible for the relevant code. Here, the answer spans detector setup, result filters and reporting.
Relevant owners investigate. Others wait.
The illustration follows file owners responsible for detector setup, result filters and reporting. Other file owners wait for relevant work.
A correct clue.
An incomplete answer.
The baseline reproduced a detector-configuration mismatch. But it did not explain how matches become reported findings.
Four missed checks concerned the notifier and result-consumption path.
The animated exchanges illustrate how file owners share evidence across the result-processing path.
Explain the whole
result path.
Which detectors ran is only the start. Filtering, deduplication and counting determine what the application reports.
The same detector execution can produce different reported counts.
A complete answer explains the notifier’s role in deduplication and metric updates, including what happens when an API caller consumes ResultsChan directly.
From a partial answer
to full marks.
We used Coral Code’s targeted question workflow to score 26/26 on the TruffleHog task, passing all answer checks.
17/26 without Coral Code. 26/26 with Coral Code.
Our research, applied
Beyond retrieving context.
Coordinate the work.
A context tool supplies information to your agent. We also distribute the investigation: agents own their part, exchange evidence, and contribute changes you can inspect.
Measured on real software tasks
100%more tasks solved.
Same DeepSeek model.
With Coral Code.
DeepSeek V4 Pro · Mini-SWE-Agent
Task success rate · zero-based 0–100% scale
2× the success rate: (54 − 27) ÷ 27 = 100%.
Compared with context tools
67/67checks passed.
We selected five tasks a single Codex agent had failed. With Coral Code, it passed every check in that sample.
Codex · DeepSeek V4 Pro
- Codex alone
- 45 / 67
- With Augment MCP
- 46 / 67
- With Graphify
- 56 / 67
- With Coral Code
- 67 / 67
Five selected, previously failed tasks. This comparison covers that sample.
About the results
We document these experiments in our September 2026 research summary. We tested Coral Code on 124 tasks using Mini-SWE-Agent and ran the AgentRadio study using Claude Code. Each experiment counts a task as solved when it passes every required check.
Product architecture and research at CoralOS ↗For engineering teams
More accepted work.
Under your control.
Our next step is paid pilots with engineering leaders, measuring accepted work, time and cost. Our commercial plan includes team subscriptions, managed AI usage and private enterprise licensing.
Explore Coral Code