RepoRadar
Leave a Tip
Item detail

usewhale/Whale

usewhale/Whale is an MIT-licensed terminal-first AI coding agent optimized for DeepSeek-class models, with a 1M-token context, MCP tool support, and a stated ~98% prompt-cache hit rate that targets the cost profile of a long-running coding session.

Open source →Back to radar
Score7.9
Popularity7.0
Riskconditional
TierGold
Score breakdown
Usefulness8.0
Novelty7.0
Momentum8.0
Maturity6.4
Open-source/build8.4
Evidence7.2
Workflow potential9.4
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for developers and platform teams who want a fast, terminal-native coding agent wired to DeepSeek's long-context models without paying per-token for a hosted equivalent.

Who should use it

developers who want a terminal-native coding agent for DeepSeekplatform teams standardizing on open-weight models for coding workloadsMCP users looking for a coding agent that consumes MCP tools cleanlyengineers who need a long-context coding session without per-token hosted cost

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

It executes shell commands and edits files in your project on behalf of an LLM, so run it in a sandboxed environment and review diffs before granting credentials or network access.

Evidence links

Closest alternatives / related signals

coding-agentdeepseekterminalmcplong-contextopen-source