CATEGORY INTELLIGENCE / WORLDWIDE
Local LLMs
Models and inference that run on your own machine.
Red ocean · Measured classification
Cooling recently, still above last year
The recent search pullback coexists with a higher level than last year. Compare concrete use cases; neither window measures customer demand.
Report dated · Method 1.2.0 · moderate evidence confidence
- 848 active projects match the published GitHub search scope.
- The keyword “local llm” has 104 complete weeks; 0% are reported as zero.
- Matching active GitHub projects
- 848
- Search-interest growth
- -73% · Last 8 complete weeks vs previous 8
- Search term and region
- local llm · Worldwide
- Complete weekly observations
- 104
Why this classification
- Search attention is cooling recently but remains above the same period last year. A pullback is not a long-term decline.
- Median weekly search interest fell 73% across two consecutive eight-week windows.
- 848 matching active repositories; this is search coverage, not a count of direct competitors.
- Four-week search change: -17%; thirteen-week change: -60%. These windows check the direction of the eight-week comparison.
Source evidence
GitHub repository search · topic:local-llm fork:false archived:false stars:>=5 pushed:>=2026-03-20
Collected 2026-09-16T04:45:38.691Z
Google Trends search interest · Collected 2026-09-16T04:45:38.687Z
Leading repositories
| Repository | Stars | Description |
|---|---|---|
| HKUDS/nanobot | 48,198 | 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 | 25,971 | Distribute and run LLMs with a single file. |
| LearningCircuit/local-deep-research | 9,097 | ~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 | 6,929 | Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it. |
| MakazhanAlpamys/Soup | 6,643 | Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. |
| dograh-hq/dograh | 5,661 | 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 | 5,328 | 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 | 4,822 | Opinionated paranoid text spacing in JavaScript, with on-device AI semantic judgment |
| langroid/langroid | 4,104 | Harness LLMs with Multi-Agent Programming |
| raullenchai/Rapid-MLX | 3,757 | 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, not customers, revenue or willingness to pay.
- Supply counts active repositories matching the displayed GitHub topic and phrase queries; unmatched and closed-source competitors are outside this coverage.
- Repository density and search attention are separate observations. Neither proves commercial competition or demand.
Search interest measures attention, not paying customers. Classification thresholds are published heuristics and still require empirical calibration.
Use and share the evidence
Permanent report · Markdown · JSON · PNG card
