- type
- Coding agent
- interface
- Not confirmed (benchmarked on Terminal-Bench 2.1, which suggests a terminal interface; not stated explicitly in available sources)
- openSource
- Not stated in available sources
- lineage
- Decomposes the coding workflow into three specialised agents, a planner, a worker and a verifier, to solve the common open-source-model failure mode of prematurely declaring a task complete; steerable long-running plan with resumable checkpoints; pay-for-completed-work billing where retries and dead ends are not charged; Sarvam's own Terminal-Bench 2.1 comparison claims about $2 per solved task versus $4.10-$27.80 for Claude Code and Codex
- note
- Unveiled at Sarvam AI's Epoch 2026 Builder Edition conference in Bengaluru on 2026-07-30, rolling out in early beta under Sarvam's Indus platform; Sarvam AI is an Indian sovereign-AI unicorn, the first India-origin entrant in the catalogue's coding-agent set
- iconUrl
- /research/harness-icons/sarvam-code.png
