Skip to main content
Open Source Organization4 Flagship Projects

PicadoLabs

Open-source developer research laboratory specializing in zero-API developer tooling, autonomous coding agents, benchmark harnesses, and local-first AI software architecture.

Picado Labs GitHubWebsitebuild-with-ai ShowcaseView All Open Source
01
Creator & Maintainer
Apache 2.0

build-with-ai

Zero-API Developer CLI & AI Workflow Engine

Open-source developer CLI guiding engineers through structured development phases with zero-API overhead and persistent local context across any AI model.

Key Engineering Deliverables
  • •Local-First Memory: Preserves architectural choices across sessions (.buildwithai/context.json) to eliminate AI context drift.
  • •Workflow Blueprints: 11 production templates spanning SaaS MVPs, REST APIs, FastAPI, Expo, Electron, Discord Bots, AI Agents/RAG, and Chrome extensions.
  • •Interpolation Engine: Dynamic prompt variable injection with strict prerequisite checks and automated clipboard sync.
Node.jsJavaScriptCLI EngineAI Prompts
02
PicadoLabs System
Apache 2.0

Terminal Agent

Verify-first autonomous software engineering agent.

An autonomous AI coding agent that plans, modifies, tests, and independently verifies real-world codebases with sandboxed isolation and automatic rollback.

Architecture Highlight

Implements a verify-first workflow by executing an independent test runner in an isolated sandbox for each code modification.

Key Engineering Deliverables
  • •Autonomous Agent Loop: LLM planning, controlled CLI execution & independent test verification
  • •Independent Verification: Separates code generation from test execution and verification inside an isolated sandbox
  • •Automatic Rollback & Recovery: Classifies failures across 12 categories with SQLite checkpoints and state snapshots
PythonDockerSQLiteGitPytest
03
PicadoLabs Benchmark
Apache 2.0

Agent Bench

Autonomous AI agent benchmarking framework.

A CLI toolkit for benchmarking AI coding agents across 40+ programming tasks using deterministic rule-based scoring and full execution trace logging.

Architecture Highlight

Automated multi-task benchmarking of AI agents with deterministic rule-based scoring for fair, non-stochastic comparison.

Key Engineering Deliverables
  • •40+ Benchmark Tasks: Real-world programming and tool-use scenarios with declarative YAML definitions
  • •Deterministic Rule-Based Scoring: Avoids stochastic LLM judging through deterministic rule-based evaluation pipelines
  • •Execution Trace Logging: Complete JSON audit trail with tool calls, timestamps, and microsecond timing
PythonCLIYAMLDockerJSON
04
PicadoLabs Proxy
Apache 2.0

Model Router

Adaptive LLM selection proxy designed to optimize inference costs through intelligent routing.

An intelligent proxy gateway that dynamically routes LLM queries based on prompt complexity—directing simpler queries to lower-cost models while reserving premium models for complex tasks.

Architecture Highlight

Engineered an adaptive LLM gateway designed to reduce API costs by dynamically routing prompts based on query complexity.

Key Engineering Deliverables
  • •Prompt-Based Model Selection: Analyzes complexity to route between local models and flagship frontier APIs
  • •OpenAI / Claude API Proxy: API-compatible gateway and proxy for standard client SDKs with unified streaming
  • •Cost-Efficient Routing: Routes simpler queries to lower-cost models while reserving premium models for complex tasks
PythonFastAPIOpenAI APIAnthropic APILocal LLMs