Browse tools registered by builders. Search by name, tag, or problem statement.
Loading...
Trust scoring and access auditing for AI agent outputs.
Sub-threshold anomaly detection. Watches event streams, trace samples, and contract violations for pattern divergence that doesn't trip any single alarm.
Organizational pattern discovery using adaptive resonance theory.
Adaptive model distillation with progressive handoff from frontier to local.
Interactive constraint elicitation. Interviews you about project boundaries before code exists.
Policy enforcement and sovereign identity for AI agents.
Contract-first multi-agent software engineering. Contracts and tests before code.
Human-in-the-loop coordination primitive. Surfaces decisions requiring human judgment, blocks until approval/rejection, captures rationale, writes audit.
Event collection and story assembly from distributed sources.
Persistent knowledge graph for AI coding assistants. Remembers across sessions so agents never start from zero.
Production monitoring, error attribution, and contract tightening.
Deterministic policy enforcement for AI agent tool calls. No LLM in the authorization path; 25ms end-to-end.
Cloud-agnostic circuit orchestration with topology-first design.
Governed code review service demonstrating the full governance stack.
AI-powered engineering management CLI. Roster, meeting transcripts, risk detection, coaching, OKR/PIP tracking, interactive TUI.
Stack adoption and compatibility scanning for existing codebases.
Emergency kill-switch service. The exemplar stack's last-resort termination mechanism. Does not negotiate, does not retry — terminates and rolls back.
Schema registry with field-level data classification.
Register-aware prompt translation.
Self-validating executable document format. The document proves itself; the engine validates the chain; nothing outside the artifact is consulted.
Embed authorization in the token. 150 lines. Zero deps. Microseconds. SPL (Safe Policy Lisp) inside signed capability tokens.
Async webhook relay and message queue for AI agents. Pull-based, encrypted, self-hostable.
Decentralized, ephemeral peer-to-peer messaging. No servers, no persistence, no compromise. PGP-style encryption, public/private channels.
ZeroGPT Plus is a free, no-login AI content detector and humanizer that identifies AI-generated text. It offers multi-language support to refine AI content into natural-sounding, human-like prose.
Contract validation runtime. Per-environment violation policy + sliding-window violation budget. Twin TypeScript + Python siblings.
Interactive demo of client-side encryption architecture. Server stores only encrypted blobs at opaque addresses; credentials never leave the client.
Resource-budget primitive. Wrap every blocking call with a declared timeout, optional fallback, and structured tags. Twin TypeScript + Python implementations.