[ CAPABILITIES ]

    Production AI builds, shipped.

    Every engagement runs the same way: honest scoping, a structured build with security gates, and full source-code ownership handed to your team. Here's the work and how we do it.

    Capabilities

    AI Systems Shipped

    Production apps with auth, billing, real data, and security from prompt one. Built fast with Lovable.

    Agents Deployed Safely

    OpenClaw with the NemoClaw security layer. Sandboxed, auditable, signed off by your CISO.

    Claude Code, Set Up Right

    CLAUDE.md, MCP servers, workspace context, so your team ships at full speed.

    The Six-Week LEAP Sprint

    Map workflows, scope the highest-leverage opportunity, ship it. Your team owns the result.

    Honest Scoping

    We tell you what's worth automating and what to skip. No AI theater, no padded scope.

    Built by an Operator

    13 years of mixed IT. Lovable Champion and community leader. Columbus, OH.

    [ PORTFOLIO ]

    What we've built.

    Real products, shipped to production. Each one built with our phase-gated methodology.

    Agent Governance · Open Source

    ClawKeeper

    Open Source

    110-agent finance platform where a deterministic policy engine runs tenant, capability, and approval checks before any LLM call. $0 default autonomous spend, database-enforced immutable audit log. MIT.

    Policy EngineImmutable AuditAI AgentsOpen Source

    Trust Contracts · Open Source

    TechTide Harness Kit

    Open Source

    Trust contracts as JSON Schema: risk tiers, tool permissions, deny-by-default egress, approval gates, compliance control mappings. Prompt-injection threat model with adversarial fixtures and ~28 CI validation gates. Apache-2.0.

    Trust ContractsDeny-by-DefaultCI GatesOpen Source

    Deterministic Debugging · Open Source

    CipherClaw

    Open Source

    Multi-agent debugger with zero LLM calls in the analysis path: causal graphs, weighted root-cause scoring, failure prediction. 206 zero-mock tests, zero runtime dependencies, no network egress. Apache-2.0.

    ObservabilityZero-LLMMulti-AgentOpen Source

    Governed Orchestration · Open Source

    Swarm 357

    Open Source

    357-agent orchestrator governed by per-agent budget caps, a pattern-matched bash security gate, auto-downgrade daily budgets, a hard per-run spend ceiling, and correlation-ID structured telemetry. Apache-2.0.

    Budget CapsSecurity GateOrchestrationOpen Source

    Trace Forensics · Private Build

    AgentRewind

    Private Build

    Time-travel debugging for agent traces: zero-trust import parsing with signature verification and size clamps, five trace formats auto-detected, and a divergence/latency/token diff engine for side-by-side replay.

    Trace ReplayZero-Trust ParsingDiff Engine

    HITL Research · Open Source

    FintheFinder

    Open Source

    Deep-research agent with a real human-in-the-loop approval workflow — the run suspends until a human approves — and a deterministic citation audit with zero AI in the verification path. PII-redacting logs.

    Approval WorkflowCitation AuditHuman-in-the-LoopOpen Source

    Governed Runtime · Private Build

    Molten

    Private Build

    Governed agent runtime: kill switch with cost and error auto-triggers, circuit breakers, a four-tier execution sandbox, hard daily and per-task budget caps, and a dead-man's switch.

    Kill SwitchCircuit BreakersSandbox Tiers

    Control-Plane Architecture · Open Source

    TechTideAI2

    Open Source

    Company-scale agent platform on a three-plane architecture — control, data, and evidence. Explicit state-machine status transitions, hard execution timeouts, and an adversarial eval harness with a 33-task golden suite.

    Control PlaneEval HarnessState MachineOpen Source