awesomer_
>

Local LLM

> Platforms, tools, practices and resources that helps run LLMs locally

## about
1
HOTTESTthis week
Niko1221 avatar

Strata

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

+5,48028.8k
2
sst avatar

opencode

The open source coding agent.

+5,249218.3k
3
obra avatar

superpowers

An agentic skills framework & software development methodology that works.

+3,940302.4k
4
mendableai avatar

firecrawl

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence.

+2,219193.2k
5
earendil-works avatar

pi

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

+1,804116.6k
6
pingdotgg avatar
t3code
+1,42628.7k
7
ollama avatar
ollamaGet up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
+994184.0k
8
p-e-w avatar
hereticFully automatic censorship removal for language models
+96236.0k
9
browser-use avatar
browser-useOpen-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
+789118.6k
10
ggml-org avatar
llama.cppLLM inference in C/C++
+785131.8k
11
NVIDIA avatar
OpenShellOpenShell is the safe, private runtime for autonomous AI agents.
+73716.8k
12
trycua avatar
cuaScale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
+73630.3k
13
open-webui avatar
open-webuiUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
+735156.2k
14
All-Hands-AI avatar
OpenHandsOpenHands: AI-Driven Development
+56491.4k
ALL REPOS189 of 189 repos
22 of 22 categories
▼ CATEGORIESall selected
sort:
repostars7d
Strata
Inference engines
28.8k+5,480
opencode
Coding Agents
218.3k+5,249
superpowers
Agents
302.4k+3,940
firecrawl
Browser Automation
193.2k+2,219
pi
Agent Frameworks
116.6k+1,804
t3code
Agent Frameworks
28.7k+1,426
ollama
Inference engines
184.0k+994
heretic
Training and Fine-tuning
36.0k+962
browser-use
Browser Automation
118.6k+789
llama.cpp
Inference engines
131.8k+785
OpenShell
Security and Sandboxing
16.8k+737
cua
Computer Use
30.3k+736
open-webui
User Interfaces
156.2k+735
OpenHands
Coding Agents
91.4k+564
playwright
Browser Automation
98.1k+533
vllm
Inference engines
94.2k+512
tokenspeed
Inference engines
2.7k+512
BrowserSkill
Browser Automation
9.3k+477
chrome-devtools-mcp
Model Context Protocol
53.9k+460
cognee
Memory Management
32.6k+436
system_prompts_leaks
Prompt Engineering
69.9k+407
mem0
Memory Management
67.5k+405
sglang
Inference engines
37.5k+402
openchamber
Coding Agents
11.9k+395
unsloth
Inference platforms
78.3k+378
langchain
Agent Frameworks
148.1k+377
context7
Miscellaneous
63.3k+377
graphiti
Retrieval-Augmented Generation
32.1k+371
cline
Coding Agents
70.6k+346
SillyTavern
User Interfaces
34.7k+334
anything-llm
Agent Frameworks
67.3k+330
langfuse
Testing, Evaluation and Observability
36.1k+325
playwright-mcp
Model Context Protocol
38.4k+311
llmfit
Models
38.2k+294
zed
Coding Agents
92.0k+286
superset
Agent Frameworks
15.4k+278
open-notebook
Research
40.4k+277
langflow
Agent Frameworks
155.9k+274
crewAI
Agent Frameworks
59.9k+268
LocalAI
Inference platforms
49.8k+255
Prompt-Engineering-Guide
Prompt Engineering
79.4k+252
goose
Coding Agents
55.5k+227
agentskills
Agents
26.3k+227
github-mcp-server
Model Context Protocol
33.8k+211
opik
Testing, Evaluation and Observability
22.8k+205
500-AI-Agents-Projects
Agents
38.8k+204
nano-vllm
Inference engines
16.0k+201
omlx
Inference engines
23.0k+200
Perplexica
Research
37.5k+190
nanochat
Models
58.8k+185
local-deep-research
Research
9.4k+182
onyx
Retrieval-Augmented Generation
32.6k+169
openai-agents-python
Agent Frameworks
30.2k+162
pydantic-ai
Agent Frameworks
20.8k+158
lobe-chat
User Interfaces
83.4k+157
presenton
Miscellaneous
11.2k+150
12-factor-agents
Agents
26.8k+137
BitNet
Inference engines
41.2k+135
aider
Coding Agents
49.7k+134
ZLUDA
Hardware
15.1k+134
openwork
Computer Use
24.2k+133
mlx-lm
Inference engines
7.4k+132
system-prompts-and-models-of-ai-tools
Prompt Engineering
144.1k+131
agno
Agent Frameworks
42.8k+131
LightRAG
Retrieval-Augmented Generation
40.2k+127
gpt-researcher
Research
30.2k+126
AutoGPT
Agent Frameworks
187.7k+123
supermemory
Memory Management
31.3k+122
SurfSense
Research
16.5k+120
agent-framework
Agent Frameworks
14.2k+116
mempalace
Memory Management
59.7k+115
LMCache
Memory Management
12.1k+115
exo
Inference engines
48.0k+114
agents.md
Agents
25.0k+114
flashinfer
Inference engines
6.7k+111
autogen
Agent Frameworks
61.5k+108
llama_index
Agent Frameworks
52.6k+105
mini-sglang
Inference engines
5.4k+104
crush
Coding Agents
28.7k+103
stagehand
Browser Automation
25.7k+93
jan
Inference platforms
45.0k+89
RAG_Techniques
Retrieval-Augmented Generation
29.9k+81
letta
Memory Management
25.2k+78
kilocode
Coding Agents
27.7k+77
RD-Agent
Research
15.0k+77
CubeSandbox
Security and Sandboxing
13.0k+77
llama-swap
Models
6.0k+77
ChatBox
Inference platforms
42.1k+73
graphrag
Retrieval-Augmented Generation
36.4k+72
GenAI_Agents
Agents
24.6k+70
garak
Security and Sandboxing
9.6k+70
miles
Training and Fine-tuning
3.2k+66
dynamo
Inference engines
8.3k+65
continue
Coding Agents
36.3k+63
camel
Agent Frameworks
17.9k+61
Agent-S
Computer Use
12.7k+61
TensorRT-LLM
Inference engines
14.9k+60
emdash
Agent Frameworks
6.0k+60
agents-towards-production
Agents
21.7k+59
lemonade
Inference platforms
5.9k+57
haystack
Retrieval-Augmented Generation
26.8k+54
open-interpreter
Computer Use
68.6k+51
nanobrowser
Browser Automation
14.1k+51
dbhub
Model Context Protocol
3.7k+51
puppeteer
Browser Automation
95.7k+50
trl
Training and Fine-tuning
19.6k+50
n8n-mcp
Model Context Protocol
23.1k+48
koboldcpp
Inference engines
12.0k+48
NemoClaw
Agent Frameworks
22.8k+46
deepwiki-open
Miscellaneous
18.2k+45
Guardrails
Security and Sandboxing
7.3k+45
gpustack
Inference engines
5.9k+43
slime
Training and Fine-tuning
8.7k+41
LiteRT-LM
Inference engines
6.7k+38
sim
Agent Frameworks
29.8k+36
outlines
Models
16.0k+34
mobile-use
Miscellaneous
3.3k+29
sentence-transformers
Training and Fine-tuning
19.2k+26
mlx-vlm
Inference engines
5.6k+26
OpenEnv
Training and Fine-tuning
2.7k+26
mcp-atlassian
Model Context Protocol
6.0k+25
gym
Training and Fine-tuning
1.3k+25
skills
Agents
11.2k+24
mcp
Model Context Protocol
9.8k+23
speakr
Miscellaneous
4.1k+23
claude-context
Retrieval-Augmented Generation
12.6k+20
genkit
Agent Frameworks
6.5k+20
ik_llama.cpp
Inference engines
3.3k+19
memU
Memory Management
14.6k+18
mistral.rs
Inference engines
7.8k+18
giskard
Testing, Evaluation and Observability
5.9k+18
kiln
Training and Fine-tuning
5.2k+18
executorch
Inference engines
5.1k+18
agenta
Testing, Evaluation and Observability
4.8k+18
OpenRLHF
Training and Fine-tuning
10.1k+17
litert
Inference engines
3.5k+16
rl
Training and Fine-tuning
2.1k+16
FastFlowLM
Inference engines
2.0k+16
OmniParser
Computer Use
25.5k+15
production-stack
Inference
2.7k+15
Flowise
Agent Frameworks
55.5k+14
humanlayer
Coding Agents
11.7k+14
openllmetry
Testing, Evaluation and Observability
7.5k+14
mindsdb
Model Context Protocol
39.8k+13
txtai
Agent Frameworks
13.0k+13
page-assist
User Interfaces
8.3k+12
Prompt_Engineering
Prompt Engineering
7.9k+12
text-generation-webui
User Interfaces
47.7k+11
pipeshub-ai
Retrieval-Augmented Generation
3.8k+11
SpecForge
Training and Fine-tuning
1.2k+11
local-deep-researcher
Research
9.4k+10
llm-scaler
Inference engines
572+10
archgw
Agent Frameworks
7.1k+9
distributed-llama
Inference engines
3.1k+7
reasoning-bank
Memory Management
619+6
tabby
Coding Agents
33.9k+5
SuperAGI
Agent Frameworks
17.7k+5
Context-Engineering
Context Engineering
9.3k+5
sonar
Inference engines
1.9k+5
local-llm
Miscellaneous
1.9k+5
Observer
Miscellaneous
1.7k+5
99
Coding Agents
4.8k+4
Awesome-Context-Engineering
Context Engineering
3.3k+4
OmniGen2
Miscellaneous
4.1k+3
bullshit-benchmark
Explorers, Benchmarks, Leaderboards
1.9k+3
maestro
Research
1.5k+3
llguidance
Models
891+3
ragbits
Agent Frameworks
1.7k+2
OpenRoom
Computer Use
1.3k+2
LLM-Agents-Ecosystem-Handbook
Agents
555+2
evaluator
Testing, Evaluation and Observability
353+2
gabber
Miscellaneous
1.1k+1
tencentdb-agent-memory
Memory Management
29.7k
cai
Miscellaneous
9.8k
ProxyAI
Coding Agents
1.9k
Controllable-RAG-Agent
Retrieval-Augmented Generation
1.6k
gguf-docs
Models
522
vllm-gfx906
Inference engines
435
augmentoolkit
Training and Fine-tuning
1.9k-1
krasis
Inference engines
522-1
4o-ghibli-at-home
Miscellaneous
490-1
self-operating-computer
Computer Use
10.3k-2
NeMo-Agent-Toolkit
Agent Frameworks
2.7k-2
ClaraVerse
Agent Frameworks
3.9k-3
Roo-Code
Coding Agents
24.3k-7
llm-app
Retrieval-Augmented Generation
58.8k-9
vanna
Retrieval-Augmented Generation
23.8k-11
void
Coding Agents
28.7k-13
pathway
Retrieval-Augmented Generation
62.1k-36