Guardrails for Pi that steer instead of interrupt: enforces your project rules on every write, holds only hard-to-undo actions (3 per 1,000 calls, measured on real sessions), catches unverified "done" claims and stuck loops, and trims tool output. Built on pi-typesafe.
☆192Nov 12, 2026Updated this week
Alternatives and similar repositories for pi-warden
Users that are interested in pi-warden are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- TypeSafe decisions for Pi: batched evaluation tool, terminal playground, and typed API for extension authors☆49Nov 4, 2026Updated last week
- Coverage, security and code quality for coding agents☆167Updated this week
- Provider-neutral System One runtime for TypeScript and Pi☆74Updated this week
- Autonomous multi-source rental search powered by TypeSafe Jev☆11Sep 21, 2026Updated last month
- Non-blocking subagent orchestration for pi. Spawn isolated agents that work in parallel while your session stays interactive.☆128Oct 18, 2026Updated 3 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- System One MCP connector to evaluate anything fast and cheap. Give your AI agent direct access to models like: Jev, D1, CLM and Laya☆361Updated this week
- Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by Type…☆13Oct 13, 2026Updated last month
- ☆21Oct 20, 2026Updated 3 weeks ago
- Jev picks which of your rules apply to each prompt, so Claude only sees the ones that matter.☆65Sep 27, 2026Updated last month
- An agent supervisor and software factory foreman powered by decision models☆825Oct 15, 2026Updated 3 weeks ago
- 👉 tmux-fingers for Herdr — type a short hint to copy, paste or open any path, URL, hash or number on screen. Rust, Clean Architecture.☆14Updated this week
- Smart, Fast & Lossless session compaction for Pi. No LLM calls - produces structured, transcript-preserving summaries using pure extracti…☆587Oct 29, 2026Updated 2 weeks ago
- Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails…☆34Oct 18, 2026Updated 3 weeks ago
- 🤠 Agent orchestrator for pi. It can manage Codex, Claude Code, OpenCode, pi, pig and pi-bolt as subagents and handover sessions in betwe…☆66Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway☆16Sep 22, 2026Updated last month
- Typesafe.ai System One Model Jev navigating a Neo4j graph by using a classifier over neighbouring relationships☆185Sep 18, 2026Updated last month
- Checkpoint/rewind extension for the Pi coding agent. 1 checkpoint per turn, /rewind command, diff preview, safe restore, redo stack.☆116Mar 31, 2026Updated 7 months ago
- Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis.☆21Oct 4, 2026Updated last month
- Breaking the quadratic memory barrier in AI☆60Oct 13, 2026Updated last month
- Use [Multi]ple AI agents for code-review, verifying and questions☆24Nov 3, 2026Updated last week
- ☆121Oct 27, 2026Updated 2 weeks ago
- Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks…☆141Oct 19, 2026Updated 3 weeks ago
- A staged code-review workflow and local dashboard built with TypeSafe Jev.☆703Sep 17, 2026Updated last month
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- pi-agent-harness — a pi coding-agent plugin/package that turns one domain sentence into a multi-agent team: specialist agents (.pi/agents…☆25Jul 1, 2026Updated 4 months ago
- Put a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit☆113Sep 17, 2026Updated last month
- Evidence-backed proof of done for Claude Code, Codex, Cursor, and other AI coding agents. Run real checks, bind results to current Git st…☆17Updated this week
- Benchmark coding agents and agent harnesses on 226 deterministic file-editing tasks with byte-exact verification and a public leaderboard…☆38Updated this week
- A provider to access a Claude code subscription via code-code in pi☆384Nov 5, 2026Updated last week
- Open-source model and reasoning effort router for Claude Code and Codex, using Jev or experimental self-hosted Laya.☆18Oct 22, 2026Updated 3 weeks ago
- A fuzzy linter for coding agents. It checks the code your agent writes against your team's best practices while the agent is still workin…☆19Updated this week
- Split-view TUI extension for the pi coding agent: thinking/tool band, files dock, response-only mode☆20Updated this week
- The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.☆922Oct 19, 2026Updated 3 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.☆15Sep 20, 2026Updated last month
- memory for the people of pi (with help of hindsight)☆42Oct 21, 2026Updated 3 weeks ago
- pi.dev profile manager. Switch between multiple sets of settings, extensions, skills, themes, auth.☆23Mar 13, 2026Updated 8 months ago
- Asynchronous Pi subagents and agent fleet orchestration for parallel coding agents with nested delegation, background work, and supervisi…☆227Updated this week
- Proof of concept: turn old Android phones into an LLM inference cluster. ADB zero-touch provisioning, llama.cpp on each phone, OpenAI-com…☆16Oct 20, 2026Updated 3 weeks ago
- Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.☆1,301Sep 29, 2026Updated last month
- TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers☆165Oct 31, 2026Updated 2 weeks ago
Are these results useful?