Catalogue
Platforms
Harnesses, frameworks, tools, apps, and platforms for agent builders, each scored on real GitHub credibility and each with a credibility-gated forum.
69 tools · showing 49–69
PlatformOpenClaw Managed Agents
Deployment
stainlu
Self-hostable Agent/Environment/Session/Event API that runs OpenClaw agents in per-session Docker containers on any model or cloud
cloudapissedocker
PlatformVivaria
QAResearch
METR
Self-hostable web app, server and CLI for running agents on tasks in sandboxed environments and analysing the runs.
clisandboxtask-environments
Ably AI Transport
Deployment
Managed realtime transport keeping agent/LLM streaming sessions continuous and resumable across disconnects and devices.
real-timewebsocketsession-continuitystreaming
Adaptive Engine
TrainingInferenceQA
RLOps platform for continuously fine-tuning, evaluating and serving specialised LLMs from production feedback (company acquired by Datadog).
rlopsfine-tuneproduction-feedback
Agent37 Cloud
Deployment
agent37-platform
Managed hosting that runs Hermes, OpenClaw, or custom agents as persistent instances behind one API
cloudmetered-billinggateway
Agentforce
CodingDeployment
Salesforce's platform for building, deploying and governing agents over CRM data, with Agent Builder and Data Cloud grounding.
salesproductivitysalesforcegovernanceagent-builder
Aperture
SecurityInference
Identity-aware AI gateway on Tailscale's network that centralizes provider credentials, model tokens and MCP access control for agents.
gatewayauthcredential-managementtailscale
Baseten
Deployment
Managed inference platform for deploying and autoscaling models behind APIs.
autoscalinggpumulti-cloud
CONFSEC
InferenceSecurity
Verifiably-private inference layer (OpenAI-compatible API) that wraps model serving in TEEs, blind signatures and attestation.
teeattestationpiiopenai-compatible
Contextual AI Platform
MemoryQA
Managed platform for building and hosting grounded RAG agents over enterprise documents, with API + GUI and built-in evals.
ragdocument-processingknowledge-managementevaluation
Glean
ResearchConnectors
Enterprise work-AI platform: permission-aware search index plus an agent builder, REST API and MCP server for organisation-aware agents.
productivityenterprise-searchagent-builderpermissionmcp-server
Heroku Managed Inference and Agents
InferenceMemory
Heroku add-on giving apps curated model inference, embeddings, pgvector storage and MCP-based agentic tool calling via the Heroku CLI.
vector-dbpgvectortool-callingheroku
Hyperbolic
Inference
Decentralised GPU marketplace plus serverless OpenAI-compatible inference API over 25+ open models, with on-demand and reserved bare-metal compute.
gpuopenai-compatibleserverlessdecentralized
Mistral Agents API
CodingConnectors
Hosted agents service with persistent conversations, MCP client support, and built-in connectors including sandboxed code execution.
mistralcode-executionsandboxconversation-state
Platformmoltbook
Interface
Social platform where AI agents post, comment and upvote in topic submolts, with humans able to observe
social-mediaagent-networksubmoltsx-verification
MutagenT
QAMonitoring
Agent-engineering platform: offline build-and-eval loops, trace diagnosis and automated optimization; official Claude Code skills at github.com/mutagent-io.
evaluationobservabilitytrace-diagnosisagent-lifecycle
Ona
CodingSecurity
Formerly Gitpod: API-first sandboxed cloud dev environments that host and orchestrate fleets of autonomous coding agents.
cloud-development-environmentsandboxcoding-agentgitpod
Polygraph
CodingMemory
Agent-agnostic meta-harness: indexes many repos into one dependency graph, persists agent sessions, and orchestrates cross-repo PRs/CI for Claude Code, Codex and OpenCode.
multi-repodependency-graphsession-managementcross-repo-ci
RunPod
DeploymentTrainingInference
GPU cloud offering Pods, autoscaling Serverless workers, multi-node Clusters and a repo-backed Hub for one-click model endpoints.
gpucloudserverlessautoscaling
SambaCloud (SambaNova Cloud)
DeploymentCoding
Hosted high-throughput inference for large open models (Llama, Qwen, DeepSeek) behind an OpenAI-compatible API.
openai-compatibleopen-weightshosted-inferencellama
Superconductor
Coding
Multiplayer workspace running many cloud coding agents (Claude Code, Codex, Pi, Amp, Cursor) in isolated sandboxes with shared sessions, previews and review.
coding-agentsandboxmulti-agentcode-review