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 169–192
ToolrLLM
TrainingQA
rllm-org
rLLM bolts RL onto agents you already wrote. verl, trlx, OpenRLHF make you rewrite the agent into their pipeline. A deco
reinforcement-learningagent-trainingsandboxdistributed-training
ToolSupabase MCP
Connectors
supabase
Model Context Protocol server connecting Supabase projects to AI assistants for managing tables, config, and queries
postgresdatabasemcp-serverquery-tool
ToolXalgorix
Security
xalgorix
Xalgorix - Autonomous AI Pentesting Agents
penetration-testingvulnerability-scannerred-teamci-integration
ToolAgency Orchestrator
Coding
jnMetaCode
Orchestrates 216+ role-based AI experts through zero-code YAML workflows, running steps in parallel across ten LLM providers
orchestrationmulti-agentagent-builderllm-provider-agnostic
FrameworkART (Agent Reinforcement Trainer)
Training
OpenPipe
Open-source GRPO reinforcement-learning trainer for multi-step LLM agents
reinforcement-learninggrpofine-tunelora
ToolCodeg
CodingInterface
xintaofei
Collaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, etc. Desktop app, self-
coding-agentdesktopmulti-agentacp
ToolCtx
CodingMemory
ctxrs
Open source Agentic Development Environment (ADE): a hackable desktop workbench for coding agents.
local-firstcoding-agentsession-managementclaude
ToolFal
InferenceGenerative MediaDeployment
fal-ai
Fast generative-media inference (image, audio, video) via fal serverless models.
serverlessgpu
ToolFlyto Core
Security
flytohub
YAML-defined automation engine with per-step tracing and replay-from-any-step, exposing browser, API, and data modules via CLI and MCP
browser-automationyamlplaywrightorchestration
ToolKimi CLI
CodingResearch
MoonshotAI
Kimi Code CLI is your next CLI agent.
clishell-commands
ToolLLM
InterfaceInference
simonw
CLI tool and Python library for running prompts, embeddings and tools against many local and remote LLMs, with responses logged to SQLite
clisqlitevector-dbplugin
PlatformTerax AI
CodingInterfaceVoice
crynta
Lightweight (7MB) Terminal-first AI-native dev workspace
productivityideclidesktopgit
ToolWebCodex
CodingInterface
yyjeqhc
Self-hosted runtime for exposing controlled project tools to ChatGPT GPT Actions and MCP clients.
gptcode-executionremote-controllocal-first
ToolWebLLM
Inference
mlc-ai
In-browser LLM inference engine running open models client-side on WebGPU with an OpenAI-compatible API
webgpubrowseropenai-compatiblejson-mode
ToolAgent Toolkit for AWS
CodingDeployment
aws
Official AWS toolkit of MCP servers, skills and plugins that help coding agents build, deploy and manage AWS applications
cloudcdkskill
ToolAgentRQ
Interface
agentrq
AgentRQ: Human-in-loop realtime conversational task manager for AI Agents.
productivityhuman-in-the-looptask-managementreal-timemobile
ToolAI DevKit
CodingMemory
codeaholicguy
The control plane for AI coding agents.
local-firstclicontrol-planememory-retrieval
ToolAnimaWorks
CodingMemory
xuiltul
One of the hardest problems in multi-agent systems is forgetting. Most frameworks hoard context until the window explode
organization-as-codemulti-agentci-cdbrain-inspired-memory
ToolFlama
InferenceInterfaceConnectors
vortico
Ollama is fine for trying a model. vLLM becomes interesting when that model has to serve traffic: many users, agent work
openai-compatiblechatbotasgi
ToolFuture AGI
MonitoringQASecurity
future-agi
OpenTelemetry-based tracing and evaluation instrumentation for voice-AI applications.
telemetryevaluationguardrailsobservability
ToolGhidra MCP
SecurityCoding
bethington
Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforceme
reverse-engineeringghidrastatic-analysismcp-server
ToolGortex
CodingMemory
zzet
Gortex indexes repositories into a code graph and tags each call edge with how it was resolved: name-only match, tree-si
code-intelligenceknowledge-graphtree-sittertoken-optimization
ToolKuna
SecurityCoding
Noelo-Lab
An agent-first decompiler designed to be refined by other agents. Kuna is written in Rust and was originally ported from Ghidra.
reverse-engineeringghidracliwasm
ToolMagnitude
Inference
magnitudedev
Your fully local, private agent. Runs models on your machine with its built-in inference engine. Works out of the box, on any hardware.
local-firstmodel-managementcli