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.
310 tools · showing 121–144
ToolSem
Coding
Ataraxy-Labs
Two functions change in a pull request. One has tests and a single caller; the other has forty callers across the codeba
semantic-difftree-sittergitcode-intelligence
ToolSmg
Coding
smg-project
Engine-agnostic gateway that routes LLM requests across self-hosted and cloud backends with cache-aware load balancing
gatewayvllmopenai-compatible
ToolSwitchyard
Inference
NVIDIA-NeMo
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility -
gatewaylitellmopenai-compatibletoken-optimization
FrameworkTradingAgents-Astock
CodingResearch
simonlin1212
A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment.
financemulti-agentlangchaina-share
ToolWegent
CodingInterface
wecode-ai
An open-source AI-native operating system to define, organize, and run intelligent agent teams
productivitycoding-agentmulti-agenttask-managementremote-execution
ToolAgent Client Protocol
Interface
agentclientprotocol
JSON-RPC protocol standardizing how coding agents talk to editors
json-rpcacpide
ToolAgentConnect
ConnectorsCoding
agentconnect-md
Tag any agent, wherever work happens, your agents work alongside your team and each other, learning as they go.
multi-agentslacksandboxgithub
ToolAgentTeams
CodingMonitoring
agentscope-ai
An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.
matrixmulti-agenthuman-in-the-loopgovernance
HarnessAnte Preview
Coding
AntigmaLabs
Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of t
clilocal-firstlightweightself-organizing
ToolCindy
CodingInterface
makecindy
Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。
productivitycomputer-uselocal-firstmulti-providerdesktop
Tooldbt MCP Server
Connectors
dbt-labs
MCP server exposing dbt Core/Fusion/Platform project context and commands to AI agents.
dbtsemantic-layersqldata-engineering
ToolDeepEval
Coding
confident-ai
Open-source framework for unit-testing and evaluating LLM apps with ready-made metrics that run locally
evaluationragpytest
ToolForkd
Deployment
deeplethe
Agent sandboxes need VM-grade isolation without booting a fresh VM every time.
sandboxmicrovmfirecrackercopy-on-write
Graphiti
Memory
getzep
Graphiti is a framework for building and querying temporal context graphs for AI agents.
knowledge-graphtemporal-graphragneo4j
ToolGuardrails
Security
guardrails-ai
Python framework that adds input/output validation guards to LLM applications and generates structured data
validationstructured-outputguardrailshub-validators
ToolKong
CodingInterface
Kong
Cloud-native, plugin-extensible API gateway with multi-provider LLM routing, MCP governance and Kubernetes-native deployment
gatewaykubernetesproxy
ToolLetta Code
MemoryConnectors
letta-ai
Letta Code versions agent memory with git … every self-edit is a commit, subagents work on isolated worktrees, conflicts
stateful-agentsmemgptgit-versioned-memorycontinual-learning
ToolMemMachine
Memory
MemMachine
MemMachine is an open-source long-term memory layer for AI agents and LLM-powered applications.
long-term-memoryknowledge-graphpersonalizationepisodic-memory
ToolMesh LLM
Deployment
Mesh-LLM
Distributed LLM inference that pools GPUs across machines and serves one OpenAI-compatible API, splitting large models across nodes
distributed-inferenceopenai-compatiblegpulocal-first
ToolOcto CLI
Interface
Mininglamp-OSS
Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.
cliopenapiapistructured-output
ToolPaddleOCR
Data Wrangling
PaddlePaddle
OCR toolkit that converts PDFs and images into structured Markdown or JSON, with text, table, formula, and layout recognition
productivityocrdocument-processingtable-recognitionvision-language-model
ToolPruna
Inference
PrunaAI
Python package that quantises, prunes, caches and compiles models to cut inference cost and latency.
quantizationpruningmodel-compressionlatency-optimization
ToolRtk
Inference
rtk-ai
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
productivitytoken-optimizationcliproxycoding-agent
ToolStrix
Security
usestrix
Autonomous AI penetration-testing agents that find application vulnerabilities and validate them with working proof-of-concept exploits
penetration-testingred-teamvulnerability-scannerctf