본문으로 건너뛰기
EarlyLore
둘러보기
평가
제품
메이커
디자인
마케팅
트렌드
시장
내 작업 공간
노트
관심 제품
아이디어
대화
MCP / Skill
IDE
피드백
신규 회원 Pro 24시간 무료
44만 개 이상의 제품 필터링
249개 세부 시장 모두 이용
로그인 / 회원가입
Toggle Sidebar
EarlyLore
AI에게 질문
⌘J
제품, URL 검색…
⌘K
한국어
가격
로그인
오픈소스 제품 및 저장소
제품
수익 증빙
카테고리
오픈소스
전체
상업용 오픈소스(COSS)
MIT / Apache
셀프호스팅
MCP & 에이전트
기간
전체 기간
카테고리
프롬프트, 평가 및 LLM 옵저버빌리티
오픈소스 라이선스
더보기
초기화
정렬
GitHub 스타
98개 프로젝트
프롬프트, 평가 및 LLM 옵저버빌리티
상업용 경쟁 제품 →
시장 트렌드 →
히어로 및 디자인 스타일 →
오픈소스 프로젝트 · GitHub 스타
프로젝트
한줄 소개
라이선스 및 스택
Stars
월간 방문
상업화 상태
작업
C
CursorLens
hamedmp/cursorlens
Insights for AI-Assisted Coding
Insights for AI-Assisted Coding
—
141
<5K
—
T
TERMINAL-BENCH
harbor-framework/terminal-bench
TERMINAL-BENCH 5 4 3 . 1 0
TERMINAL-BENCH 5 4 3 . 1 0
Apache
·
Go
132
157.7K
—
V
VerifyWise
COSS
bluewave-labs/verifywise
Know every AI system you are running.
Know every AI system you are running.
—
105
37.3K
—
S
Switch
sandbox-quantum/switch
Switch AI is how you manage your agentic workforce.
Switch AI is how you manage your agentic workforce.
Apache
·
JavaScript
92
<5K
—
R
Raindrop
MCP
raindrop-ai/workshop
Detect agent issues. Prevent them from happening.
Detect agent issues. Prevent them from happening.
—
91
42.8K
$299/월
C
ClawMetry
COSS
vivekchand/clawmetry
Every agent. Every machine. Under control.
Every agent. Every machine. Under control.
MIT
·
Go
65
<5K
$9/월
A
ArmorClaw
armoriq/armorclaw
ArmorClaw by ArmorIQ
ArmorClaw by ArmorIQ
MIT
·
JavaScript
58
<5K
—
P
Prompt Minder
COSS
aircrushin/promptMinder
An Open-sourced "All In One" Prompt Management Platform
An Open-sourced "All In One" Prompt Management Platform
MIT
·
JavaScript
56
<5K
—
P
PandaProbe
COSS
chirpz-ai/pandaprobe
The Stack for Self-Repairing Agents
The Stack for Self-Repairing Agents
—
54
<5K
$29/월
O
Oso Cloud
COSS
osohq/oso
Visibility and controls to secure agents.
Visibility and controls to secure agents.
ISC
·
JavaScript
51
28.1K
$15/월
W
Web Bench
Halluminate/WebBench
Compare and benchmark different AI web browsing agents. Web Bench provides comprehensive performance metrics for AI agents navigating the web.
Compare and benchmark different AI web browsing agents. Web Bench provides comprehensive performance metrics for AI agents navigating the web.
MIT
·
Go
51
<5K
—
O
Output
growthxai/output
AI development at the speed of conversation.
AI development at the speed of conversation.
Apache
·
JavaScript
48
<5K
—
E
Extra Headroom
COSS
gglucass/headroom-desktop
Headroom cuts your Claude Code & ChatGPT Codex token costs ~50%
Headroom cuts your Claude Code & ChatGPT Codex token costs ~50%
—
40
47.9K
$635.12
S
Sinaptic™ AI
SinapticAI/droid-community
You cannot be everywhere.
You cannot be everywhere.
—
37
<5K
—
T
Tracely
MCP
Jwuthri/Tracely-ai
Production failures become regression tests.
Production failures become regression tests.
MIT
·
Go
37
<5K
$49/월
C
ChessArena.ai
MotiaDev/chessarena-ai
Leaderboard
Leaderboard
—
35
<5K
—
W
WhyLabs
whylabs/whylabs-oss
Run AI with Certainty
Run AI with Certainty
—
34
<5K
—
A
Agentmemoryleaderboard
AML-memory/agent-memory-leaderboard
Measure what your agents remember. Compare what truly matters.
Measure what your agents remember. Compare what truly matters.
—
31
7.3K
—
R
Rudel
COSS
obsessiondb/rudel
Pull back the curtain on your coding sessions.
Pull back the curtain on your coding sessions.
MIT
·
JavaScript
30
<5K
$85/월
M
MobileGym
Purewhiter/mobilegym
MobileGym : A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
MobileGym : A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research
Apache
·
Go
29
<5K
—
G
Google Sheet Waitlist
dambrubaba/google-sheet-waitlist
Everything for Prompts
Everything for Prompts
—
26
<5K
—
F
FrontierHarness Eval
frontier-harness-eval/eval
Comprehensive harness evaluation
Comprehensive harness evaluation
Go
25
<5K
—
A
Agentsmith
COSS
chad-syntax/agentsmith
DEVELOP AGENTS WITHPEACE OFMIND
DEVELOP AGENTS WITHPEACE OFMIND
JavaScript
24
<5K
$10/월
L
Logify360
COSS
open-telemetry/semantic-conventions-genai
Your LLM bill. Explained.
Your LLM bill. Explained.
Apache
·
Go
23
<5K
$29/월
T
TMA1
MCP
tma1-ai/tma1
Close the looparound your agent.
Close the looparound your agent.
Go
21
<5K
—
R
Rampart
peg/rampart
Let agents move fast. Keep the final say.
Let agents move fast. Keep the final say.
Go
20
<5K
—
B
BenchLLM
v7labs/BenchLLM
The best way to evaluate LLM-powered apps
The best way to evaluate LLM-powered apps
MIT
·
Python
20
<5K
—
F
FRAI
COSS
sebuzdugan/frai
Proof of what your support bot tells customers.
Proof of what your support bot tells customers.
—
18
<5K
$745/월
P
Paritok
COSS
Paritok-official/paritok-4b-v1
Supercharging your building in the AI era
Supercharging your building in the AI era
Apache
·
Python
16
<5K
—
T
TokenTelemetry
VasiHemanth/tokentelemetry
Understand what your agents actually did.
Understand what your agents actually did.
—
15
<5K
—
2 / 4 페이지 · 31–60 / 전체 98 개 오픈소스 프로젝트
이전
1
2
3
4
2 / 4
다음