Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for developers and AI-coding-agent teams who want a maintained MIT agentic-coding harness from a lab with a proven RAG track record (HKUDS/LightRAG, HKUDS/DeepTutor, HKUDS/AgentSpace are already canonical), for anyone evaluating a real MIT alternative to closed-pipeline code-generation harnesses that ships multi-agent orchestration + loop engineering + code-understanding in one surface
Where this stands now
HKUDS/DeepCode ranks #17 of 33 tracked Coding Agents items by composite score (8.0 against a section median of 8.0). The section currently carries 20 Gold, 10 Silver, 3 Bronze. RepoRadar has retained observations for this record since 2026-08-14 (30 days in the current window). Signal extremes versus the section: momentum at the 76th percentile.
Who should use it
Who should skip it
Skip HKUDS/DeepCode unless the captured evidence suggests it solves a problem you are actively working on.
About this signal
HKUDS/DeepCode is tracked by RepoRadar as a framework in the Coding Agents section. First seen 2026-08-14; the source record was last checked on 2026-08-14. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. HKUDS/DeepCode leads on workflow potential (9.5) and maturity (8.8); its lowest signal is setup ease (6.8), so factor that in before investing setup time. This page summarizes the evidence RepoRadar captured from https://github.com/HKUDS/DeepCode.
How this item is evaluated
The HKUDS/DeepCode record combines a 8.0/10 composite score with separate popularity (100.0), risk (low), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
agentic-coding outputs require human review -- verify the verifiable-code-generation claim on real tasks before scaling; the bootstrapper hands off to Claude Code / Codex / OpenCode when they are on the PATH, which means the harness assumes a coding-agent CLI is installed and authenticated; SOTA benchmark claims in the README are author-reported -- validate against your own tasks before adopting as the default surface.