CATEGORY INTELLIGENCE / WORLDWIDE
Local LLMs
Models and inference that run on your own machine.
Red ocean · Measured classification
Search falling · established alternatives
Established open-source alternatives shape this category. Compare their strengths and find a concrete reason for users to choose your product.
Report dated · Method 2.0.0 · moderate evidence confidence
Measured search term: local llm · Last 8 complete weeks vs previous 8
- 3033 active projects match the published GitHub search scope.
- The keyword “local llm” has 104 complete weeks; 0% are reported as zero.
- Competition pressure
- ≥90 / 100 · Established alternatives
- Direct alternatives
- 29
- Direction basis
- Recent search windows
- Matching active GitHub projects
- 3,033
- Search-interest growth
- -72% · Last 8 complete weeks vs previous 8
- Search term and region
- local llm · Worldwide
- Complete weekly observations
- 104
Research brief
Search attention for local LLM is falling over the recent eight weeks while the same-period annual change shows a similar level. Open-source supply stays established, and the pending review points to sample coverage still being gathered.
- Compare a specific switching advantage against observed open-source alternatives.
- Run a small, focused experiment around one workflow relevant to the product intent.
- Refine a same-intent search and examine the specific projects surfaced.
AI interpretation of the evidence below. Verify the sources before acting.
Why this classification
- Median weekly search interest fell 72% across two consecutive eight-week windows.
- 3,033 active repositories match this search scope. Review their users and workflows to identify direct alternatives.
- Four-week search change: -13%; thirteen-week change: -61%. These windows check the direction of the eight-week comparison.
- Project roles: 29 direct alternatives, 29 adjacent projects, 5 resources, 37 awaiting review.
- Competition pressure: 91–100/100; breadth 41, established alternatives 30, leading project strength 20.
Source evidence
GitHub repository search · topic:local-llm fork:false archived:false stars:>=1 pushed:>=2025-09-17
Collected 2026-09-17T05:29:25.856Z
Google Trends search interest · Collected 2026-09-17T05:29:25.856Z
Leading repositories
| Repository | Stars | Description |
|---|---|---|
| HKUDS/nanobot | 48,240 | Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps |
| mozilla-ai/llamafile | 25,977 | Distribute and run LLMs with a single file. |
| LearningCircuit/local-deep-research | 9,098 | ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted. |
| open-multi-agent/open-multi-agent | 6,933 | Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it. |
| MakazhanAlpamys/Soup | 6,721 | Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. |
| dograh-hq/dograh | 5,680 | Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support. |
| maziyarpanahi/openmed | 5,331 | Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 2,200+ medical models, 21 languages, Apple MLX + Python, no cloud, no patient data leaving your network. Apache-2.0 |
| vinta/pangu.js | 4,826 | Opinionated paranoid text spacing in JavaScript, with on-device AI semantic judgment |
| langroid/langroid | 4,103 | Harness LLMs with Multi-Agent Programming |
| raullenchai/Rapid-MLX | 3,764 | The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider. |
Limits of this result
- Google Trends measures relative search attention. Assess customers, revenue and willingness to pay through direct research.
- Supply covers active repositories matching the displayed GitHub queries. Broader competition research can include other repositories and commercial products.
- Repository density and search attention provide complementary research signals. Assess competition and demand through user and product evidence.
- Competition pressure is an operational index of observed open-source alternatives. Stars and forks indicate developer attention and reuse; user adoption and commercial products deserve separate research.
- The displayed projects form a stars-ranked sample. Competition pressure is a lower bound; wider coverage can strengthen the assessment.
- Some project roles await closer review. The pressure range includes their possible contribution.
Search interest measures attention. Customer demand needs user research; classification thresholds are published heuristics subject to empirical calibration.
Use and share the evidence
Permanent report · Markdown · JSON · PNG card
