--- title: "deep-research vs lever" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/dzhng-deep-research-vs-niansong1996-lever" tools: ["dzhng-deep-research", "niansong1996-lever"] --- # deep-research vs lever *GraphCanon updated Jul 11, 2026* ## Verdict Pick deep-research when deep-research is primarily TypeScript; lever is Python; pick lever when lever is primarily Python; deep-research is TypeScript. [deep-research](https://github.com/dzhng/deep-research) reports 19k GitHub stars, 2.0k forks, and 90 open issues, last pushed Apr 11, 2026. [lever](https://arxiv.org/abs/2302.08468) has 90 stars, 8 forks, and 2 open issues, last pushed Jul 5, 2023. Figures are from public GitHub metadata via [deep-research's repository](https://github.com/dzhng/deep-research) and [lever's repository](https://github.com/niansong1996/lever). | | [deep-research](/tools/dzhng-deep-research.md) | [lever](/tools/niansong1996-lever.md) | | --- | --- | --- | | Tagline | An AI-powered research assistant that refines its topic focus over time using search engines, web scraping, and large language models. | Code for paper "LEVER: Learning to Verifiy Language-to-Code Generation with Execution" (ICML'23) | | Stars | 19,329 | 90 | | Forks | 1,972 | 8 | | Open issues | 90 | 2 | | Language | TypeScript | Python | | Adopt for | Deep-research is an AI-powered research assistant that leverages search engines, web scraping, and large language models to conduct iterative and in-depth exploration of topics. | - | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | AI Agents, Data & Retrieval | Data & Retrieval | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [deep-research](/tools/dzhng-deep-research.md) | [lever](/tools/niansong1996-lever.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Dormant (18%) | | Days since push | 90d | 1102d | | Open issues (now) | 90 | 2 | | Security scan | 39 low (39 low) | No criticals | | Full report | [trust report](/tools/dzhng-deep-research/trust.md) | [trust report](/tools/niansong1996-lever/trust.md) | ## Decision facts: deep-research - **Requirements:** Requires Docker - **Adopt for:** Deep-research is an AI-powered research assistant that leverages search engines, web scraping, and large language models to conduct iterative and in-depth exploration of topics. ## Choose when ### Choose deep-research if… - deep-research is primarily TypeScript; lever is Python. - Requirements: Requires Docker. - Tags unique to deep-research: agent, ai, gpt, o3-mini. - Also covers AI Agents. - deep-research ships Docker support for self-hosted deployment. - When you need a tool that can refine its topic focus over time through repeated iterations. ### Choose lever if… - lever is primarily Python; deep-research is TypeScript. - Tags unique to lever: python. - Leaner open-issue backlog (2). ## When NOT to use deep-research - When you prefer a language other than TypeScript, as deep-research specifically requires a Node.js environment. - If your use case does not necessitate the use of both Firecrawl and OpenAI APIs, preferring instead solutions with more API flexibility or that do not require API keys. ## When NOT to use lever - Last GitHub push was 1103 days ago (dormant maintenance, Jul 5, 2023). Validate activity before betting a new project on lever. - Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough. ## Common questions ### What is the difference between deep-research and lever? deep-research: An AI-powered research assistant that refines its topic focus over time using search engines, web scraping, and large language models.. lever: Code for paper "LEVER: Learning to Verifiy Language-to-Code Generation with Execution" (ICML'23). See the comparison table for live GitHub stats and shared categories. ### When should I choose deep-research over lever? Choose deep-research over lever when deep-research is primarily TypeScript; lever is Python; Requirements: Requires Docker; Tags unique to deep-research: agent, ai, gpt, o3-mini; Also covers AI Agents; deep-research ships Docker support for self-hosted deployment; When you need a tool that can refine its topic focus over time through repeated iterations. ### When should I choose lever over deep-research? Choose lever over deep-research when lever is primarily Python; deep-research is TypeScript; Tags unique to lever: python; Leaner open-issue backlog (2). ### When should I avoid deep-research? When you prefer a language other than TypeScript, as deep-research specifically requires a Node.js environment. If your use case does not necessitate the use of both Firecrawl and OpenAI APIs, preferring instead solutions with more API flexibility or that do not require API keys. ### When should I avoid lever? Last GitHub push was 1103 days ago (dormant maintenance, Jul 5, 2023). Validate activity before betting a new project on lever. Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough. ### Is deep-research or lever more popular on GitHub? deep-research has more GitHub stars (19,329 vs 90). Stars measure visibility, not whether either tool fits your constraints. ### Are deep-research and lever open source? Yes - both are open-source projects on GitHub (deep-research: MIT, lever: MIT). ### Where can I find alternatives to deep-research or lever? GraphCanon lists graph-backed alternatives at [deep-research alternatives](/tools/dzhng-deep-research/alternatives) and [lever alternatives](/tools/niansong1996-lever/alternatives) ([deep-research markdown twin](/tools/dzhng-deep-research/alternatives.md), [lever markdown twin](/tools/niansong1996-lever/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/dzhng-deep-research-vs-niansong1996-lever.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, deep-research or lever? deep-research: Slowing. lever: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for deep-research and lever? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [deep-research trust report](/tools/dzhng-deep-research/trust); [lever trust report](/tools/niansong1996-lever/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=dzhng-deep-research`](/api/graphcanon/graph?tool=dzhng-deep-research) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_