Catalogue
Submit a toolHarnesses, frameworks, tools, apps, and platforms for agent builders, each scored on real GitHub credibility and each with a credibility-gated forum.
18 tools
ToolLangfuse
MonitoringQA
langfuse
Open-source platform for tracing, evaluating, and debugging LLM applications, self-hosted or cloud
observabilityevaluationpromptlocal-first
ToolOpenLIT
MonitoringSecurity
openlit
Open-source AI engineering platform with OpenTelemetry-native LLM observability, evaluations, and prompt management
telemetryevaluationpromptguardrails
ToolOpik
Monitoring
comet-ml
Open-source platform for tracing, evaluating, and monitoring LLM and agentic applications
observabilityevaluationpromptlangchain
FrameworkDSPy
CodingTraining
stanfordnlp
Compose LM pipelines as declarative Python modules, then optimize their prompts and weights algorithmically
promptragself-improvement
ToolPhoenix
Monitoring
Arize-ai
Open-source AI observability platform for tracing, evaluating, and troubleshooting LLM and agent applications
observabilityevaluationllmopsrag
ToolFabric
CodingInterface
danielmiessler
Open-source framework that organizes task-specific AI prompts, called Patterns, for use from the CLI or other tools
productivitycliprompt
FrameworkApm
Coding
microsoft
An open-source, community-driven dependency manager for AI agents.
package-managerdependency-managementskillcli
ToolLLM Space
CodingQA
deer-flow
A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first
desktopobservabilitydebuggingprompt
ToolSkillOpt
Coding
microsoft
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, valid
promptskillself-improvementreflection
ToolSuperClaude
Coding
SuperClaude-Org
Layers slash commands, specialized agents, behavioral modes, and MCP integrations onto Claude Code
skillmulti-agentpromptagent-modes
PlatformBraintrust
QAMonitoring
braintrustdata
Eval, logging and prompt-playground platform for LLM and agent applications.
evaluationobservabilityprompt
ToolAgent SOP
Coding
strands-agents
Natural language workflows that enable AI agents to perform complex, multi-step tasks with consistency and reliability.
orchestrationpromptstrands-agents
ToolCodex-X
CodingInterface
yynxxxxx
OpenAI Codex 桌面端/CLI 的可视化管理工具，具有Provider/API 切换、会话同步、提示词注入、Skills/MCP 管理、TOML 配置可视化的跨平台工具。
desktopconfig-managementpromptsession-management
HarnessWeco CLI
Coding
WecoAI
Command-line agent that iteratively writes, evaluates and optimises code against a metric.
code-optimizationpromptcligpu-kernels
PlatformHelicone
InferenceMonitoring
Acquired
Helicone
AI gateway to 100+ models with routing and fallbacks, plus request logging, tracing, and cost analytics
gatewayfallbackscost-analyticsobservability
ToolLaconic
Coding
GabrielBarberini
A 300-word brevity skill that makes coding agents answer tersely, cutting output tokens
token-optimizationprompt
ToolHermes Agent Self-Evolution
CodingQA
NousResearch
Evolves Hermes Agent skills and prompts with DSPy and GEPA, gated by tests and human PR review
dspygepapromptpull-request
AppNextChat
Interface
ChatGPTNextWeb
Cross-platform AI chat client for Claude, GPT-4, Gemini, and DeepSeek, with local storage, prompt templates, and one-click deploy
chatbotdesktopmobilelocal-first