|
The Verification Playbook — make your coding agent prove its work
A field manual and working toolkit for engineers who run AI coding agents on real codebases: turn “the agent said done” into changes you can actually trust.
|
84 % |
|
clu. agents are the commodity. context is the moat.
The central context layer for software engineering. Built for engineers running fleets of agents.
|
83 % |
|
KyberAgent — an autonomous personal agent you can audit
KyberAgent is an open-source autonomous personal agent: ontologies and graphs for what it knows, a homeostat for staying in range, policies for what it may do.
|
83 % |
|
LumenHive
LumenHive builds a memory engine that records how every fact an agent holds was learned, and a working discipline that decides what the agent may do with it.
|
83 % |
|
Scanduit · Agent provenance
An LLM proxy that records every call your agents make. Tool calls, reasoning, tokens, model, identity. One base_url change.
|
82 % |
|
Anthony Lewis
I build delivery systems that let AI agents ship software you can still account for.
|
82 % |
|
Unbounded AI — Are you interested in building agents that remember?
Unbounded AI builds memory infrastructure for AI agents. Request early access.
|
82 % |
|
forefetch: memory that answers before the question
Anticipatory memory for multi-agent pipelines. forefetch learns your pipeline's rhythm and has context at the agent's side before it asks. Measured, not clai...
|
82 % |
|
VulnWar
|
82 % |
|
Orisan
Local-first security instruments for AI agents. The first, mcpscan, reads what an MCP server exposes — tools, resources, prompts — before an agent connects.
|
81 % |
|
EffectiveFrom: effective-dated content for AI agents
The content layer for AI agents: they only get the policies, term sheets and prompts in force today, and you can show what was in force on any given date.
|
81 % |
|
Engram Protocol — Git for your agent's beliefs
Engram Protocol is the typed-state memory layer for long-lived AI agents — memory you can inspect, attribute, and correct. An agent with Engram isn't smarter...
|
81 % |
|
Match Cut
A music video archive searchable by visual grammar, with 49,753 reasoned connections. Ask, or let the agent programme a run and say why it goes where it goes.
|
81 % |
|
skemify
Turn any dataset into a schema an AI agent can navigate — powered by a curiosity-driven ingestion harness.
|
81 % |
|
Tessera — One workforce, made of many
Tessera turns a pile of separately-running agents into one accountable workforce — who's doing what, what it implies for everyone else, and where each agent'...
|
81 % |
|
Jakub Roman
I build open tools for understanding your data. The AI is the easy part.
|
80 % |
|
Serspace — A personal agent that gets you. An architecture that protects you.
Serspace Resolve. An agent that gets you. Architecture that protects you.
|
80 % |
|
Keelnote — A roadmap that builds itself as your agents work.
A roadmap that builds itself as your agents work. Keelnote is the shared, living record of why things were built, what was actually done, who asked, and what...
|
80 % |
|
Dandy AI, the state layer for agent-built software
One live, typed map of your system that every agent and every engineer works from. Agents keep it current as they build; every change is checked against what...
|
80 % |
|
Hebbrix - Persistent Memory for AI Agents
Build AI agents with persistent memory in minutes. Hebbrix provides production-ready memory infrastructure so your agents remember, learn, and improve - with...
|
80 % |
Detected social media networks