|
todox — working memory for developers and their agents
todox is a working memory for developers and their coding agents: projects, tasks, and the log that survives every session.
|
84 % |
|
Convoy - Self-healing AI agents
Convoy learns what good and bad look like from your code and the runs you flag, watches every agent run in production, ships the fix, and validates it on rea...
|
82 % |
|
Your agent said it worked. Did it? — Unreached
I get into your agent with you and find the places it reports success without proving it. One day, together, in your codebase. A successful tool call is not...
|
81 % |
|
Offlid | Choose what deserves an agent
Offlid is a private preview of a contribution desk for choosing which issues and briefs deserve an agent, then judging the proof that returns.
|
80 % |
|
Rebase — bug reports your coding agent can fix
The context layer between whoever finds a bug and whatever fixes it — one script tag, a causal timeline, a suspected file and line, handed to your agent.
|
80 % |
|
Reticle · Make your coding agent verify its own work
Make your coding agent verify its own work, and not by asking it. Reticle is AI app testing that runs inside your app: it walks the flow the way a user would...
|
80 % |
|
Hivemind — Run agents in parallel. Break nothing.
Hivemind runs coding agents side by side, keeps each one in its lane, and stops bad changes before they hit your branch.
|
80 % |
|
Invarium AI — The behavioral testing layer
Your agents pass evals. They look production-ready. Then they skip steps, hallucinate sources, and ignore guardrails — silently.
|
80 % |
|
remit.sh
The intent layer for AI agents. Remit gives every agent session a declared scope and checks every tool call against it — so off-task work can't reach what it...
|
80 % |
|
Bullseye — the org-wide intent layer for AI-assisted engineering
Bullseye captures the why behind your org's decisions — including what you tried and rejected — and serves it as living context to your coding agents. So the...
|
80 % |
|
Couldi — the machine proposes, you decide
Your attention is the bottleneck now, not the agents. Couldi Manage is the one board every agent proposes to. Couldi Build makes the thing you decided on — i...
|
80 % |
|
Chanly
The agent platform that shows you everything. Visual, open, controllable, transparent — built for SMBs and AI startups.
|
80 % |
|
CanOpener — a shared execution-experience layer for stuck AI agents
CanOpener is a queryable, community-accumulated layer of real execution experience for AI agents. When a tool call fails or two tools disagree, an agent quer...
|
80 % |
|
studio
AI-native internal systems for the teams that run the business.
|
80 % |
|
Hunch — Shared memory for AI agents
Every AI session starts from zero. Hunch keeps your team’s decisions, finished work and open commitments — with sources, in Git — so the next agent picks up...
|
80 % |
|
Assevra — Find agent failures before your users do
Open-source agent evaluation with actionable findings, explicit release gates, and portable evidence. Connect captured runs, fix failing cases, and verify th...
|
80 % |
|
Common Sense Engine — Catch the helpful mistake before it ships
Your agent doesn't need a lecture. It needs a memory of the last time 'helpful' cost real money — checked in under 100ms, before the tool runs.
|
80 % |
|
Common Sense Engine — Catch the helpful mistake before it ships
Your agent doesn't need a lecture. It needs a memory of the last time 'helpful' cost real money — checked in under 100ms, before the tool runs.
|
80 % |
|
Adkins Enterprises — Integration Diagnostics & Repair
Your webhooks and API integrations fail silently. We catch it fast, prove exactly what broke, and — if you want it — make sure it doesn't happen again unnoti...
|
79 % |
|
contextune | Behavioural context SDK for AI agents
Your agents are flying blind. Open source SDK that captures live behavioural cues and injects them into your agent system prompt. Three lines, no collector.
|
79 % |
Detected social media networks