|
Halfhand — Replay Every Action Your Agents Took
Halfhand is a local-first developer tool for recording, replaying, and debugging AI agent execution. Inspect prompts, tool calls, MCP traffic, file modificat...
|
82 % |
|
Poggle | Shared memory for coding agents
Poggle is shared memory for coding agents. Agents log what they do as they do it, so the next one — different tool, different account, different machine — pi...
|
81 % |
|
continuous-improvement · Claude Code that gets sharper every session
A runtime gate before every edit, proof before every done, and a ledger that carries each lesson into the next session. The 7 Laws of AI Agent Discipline for...
|
81 % |
|
Tracewell — Memory your AI tools can cite
Tracewell is a local-first memory layer for people who work across several AI assistants and coding agents. Find what was said and decided, with the source a...
|
81 % |
|
TraceForge — Session Replay, Heatmaps & Revenue Impact
Session replay, heatmaps, funnels, error tracking and revenue impact in one platform — plus TraceForge AI, an MCP server and expert analysis. Book a demo.
|
80 % |
|
ralph | ralph
AI-agnostic agentic loop CLI. Reset context, persist learnings, ship code.
|
80 % |
|
Singularity — AI Agent Supervision
Singularity is a desktop app that supervises your AI coding sessions so you don't have to babysit them. Free to monitor, $20 Pro one-time. Fully local. No su...
|
80 % |
|
AgenTrace — Your agent never has to start from scratch again
Stop watching your agent roam the repo wasting tokens every session. AgenTrace feeds context before the first prompt — so it picks up exactly where you left...
|
80 % |
|
Tellur — Know how AI participated in your codebase
Local-first AI code provenance: line-level attribution, tamper-evident session history, PR risk reports, and an optional self-hosted Team Hub.
|
80 % |
|
Deployment Paused
|
80 % |
|
Codevalanche | The local-first workspace for AI coding
Codevalanche is a local-first workspace for serious AI coding. Keep the repository, runtimes, and review loop together on your machine.
|
80 % |
|
AufsichtAI - A guard that checks your AI agent's work
AufsichtAI (Auf-ziht) sits between your coding agent and your repo. Every move is checked, every result is verified, and a failed result never reaches your f...
|
80 % |
|
RunLedger — The black box recorder for AI agents
Shareable receipts for every AI agent run: files changed, cost per step and a risk score. A real-time guard blocks risky commands and asks for approval. Open...
|
80 % |
|
SheryLabs — Autonomous systems that execute.
Solo-architect engagements building autonomous systems that execute workflows end-to-end. Modern full-stack, native iOS, Python AI/agentic, marketing enginee...
|
79 % |
|
Appliqation | The Quality Layer for AI-Accelerated Development
AI changed how code is written. It's time to change how it's tested. Appliqation is the quality layer for AI-accelerated development.
|
79 % |
|
EDITH — Every Deploy Inspected. Thoroughly. Honestly.
EDITH audits AI-built Next.js apps — security, SEO, AI-surface, performance, accessibility, dependencies. Writes fix prompts for Cursor, Claude Code, and Win...
|
79 % |
|
Lazy Pants Recorder
Real-time AI meeting copilot and knowledge capture
|
79 % |
|
Agent Workbench
Run DeepSeek V4 agentic workflows over entire codebases, contracts, and document sets. 1M token context. No setup. Pay per use.
|
79 % |
|
ait-native — Repository workflow for coding agents
Turn parallel coding-agent sessions into verified, traceable Tasks with isolated worktrees, repository checks, safe integration, and durable intent.
|
79 % |
|
ctxpilot — Memory engine for AI coding agents
Cut repeated AI coding context with a local memory engine, token analytics, and Claude Code beta hooks.
|
79 % |
Detected social media networks