|
RakanLabs - Your Friendly Neighbourhood Techies
I build AI systems that run in production and deliver measurable results. Not demos. Not research. Systems you can rely on.
|
84 % |
|
Pareto — Agent Observability
Pareto shows engineering teams exactly what their AI agent did — and what to fix first. Every trace comes back scored, risk-flagged, and with ranked recommen...
|
83 % |
|
agentd — a small, MCP-native agent runtime
agentd is a minimal agent runtime: one static binary that takes an instruction and tools from remote MCP servers over HTTPS and runs the agentic loop — as a...
|
83 % |
|
Harn: the pipeline-oriented language for AI agent orchestration
Harn is a pipeline-oriented language for building, orchestrating, and operating AI agents. Tutorials, guides, and a complete language and runtime reference.
|
83 % |
|
AI Agent Pipeline
|
83 % |
|
agentling · The agent framework you can read in one sitting
A tiny async framework for reliable, observable, tool-using agents.
|
83 % |
|
Kerniv — Agentic engineering, with a definition of done.
Kerniv builds and operates agentic software systems for engineering teams that cannot ship guesswork. Objective functions, deterministic verification, and a...
|
83 % |
|
Orq AI - Ship agent changes without guessing
Orq AI traces every agent run, scores it against your eval suites, and holds the release when a regression shows up. Ship AI agent changes with confidence.
|
82 % |
|
Jake McInerney — Full-Stack Software Engineer, LLM & Agentic Systems
Local-first RAG pipelines, MCP tooling, and human-in-the-loop agents with measured run costs — built by a full-stack engineer who also scopes the POC, runs t...
|
82 % |
|
The MCP Company - Infrastructure for the Agentic Web
MCP observability and security infrastructure. mcp-observe gives you full visibility into every tool call your AI agents make: inputs, outputs, latency, erro...
|
82 % |
|
Agent Doctor
Observe, experiment, and debug your AI agent pipelines
|
82 % |
|
AgentDbg | Local-first debugger for AI agents
Debug AI agent runs locally with a step-by-step timeline of LLM calls, tool calls, errors, and loop warnings. Stop runaway runs with built-in guardrails.
|
82 % |
|
Kodel — Control layer for coding agents
Describe AI-assisted dev workflows as code. Run agent → check → human gate pipelines with full observability. SaaS out of the box; self-hosted for Enterprise.
|
82 % |
|
Agent Machines | Open-source building blocks for agent harnesses.
Open-source building blocks for agent harnesses. Configure runtimes, tools, memory, and compute; run real agent CLIs in your browser; inspect and extend the...
|
82 % |
|
Bespoke Prompting — your personal AI prompt engineer
Turn any idea into an engineered AI spec: a prompt, agent, workflow, pipeline, multi agent system or MCP tool. 3 day free trial, no card required.
|
82 % |
|
Sentinel AI — independent security testing for production AI systems
Independent security testing for production AI systems. Assessment, hardening, and deployment on your own infrastructure.
|
82 % |
|
Ziro: an agent that runs on your machine
Ziro is a terminal agent runtime that runs on your machine. Memory, tools, guardrails, and MCP servers, configured in YAML files you can read.
|
82 % |
|
AgentLineage | Runtime data lineage for AI agents
AgentLineage tracks sensitive data through agent code and blocks unsafe egress at runtime.
|
82 % |
|
Aegis — Runtime capability enforcement for AI agents
Aegis is a deterministic capability-enforcement layer for AI agents on MCP. No LLM in the enforcement path. Every tool call evaluated against a spec, with a...
|
82 % |
|
Relios AI — Self-improving AI agents
Ship agents like software. Improve them like research. Relios is the control plane for self-improving AI agents.
|
82 % |
Detected social media networks