|
DeepBlame
Which AI agent wrote this line, why, and what it cost. Undo just that agent's work. Open-source CLI, works with every coding agent.
|
87 % |
|
RunOrNot — coming soon
Autonomous coding agents are being handed production access faster than anyone can supervise them. RunOrNot is a containment boundary for agent sessions. Com...
|
85 % |
|
agentc
agentc compiles declarative agent manifests into durable, production ready artifacts. Checkpointed graph execution means your agents recover from any failure...
|
85 % |
|
Stord | Undo agent file changes
Open-source CLI that records file reads and writes from coding agents, attributes them to the agent, and lets you reverse changes from the terminal.
|
85 % |
|
Open-Source Infrastructure for AI Agents | git.agentic
Version control, parallel source control, and software supply-chain security for AI agents. Explore three open-source projects from git.agentic.
|
85 % |
|
plumb: one workspace, every agent, zero collisions
Plumb is the workspace layer for AI coding agents: real IDE intelligence from the language servers your editor trusts, plus the write-safety that lets a flee...
|
85 % |
|
knoot: multiplayer for AI coding agents
knoot makes coding agents multiplayer. Every agent on a team sees what the others are doing, inherits what they have learned, and is stopped before two of th...
|
85 % |
|
kadence: shared memory for coding agents, in your git repo
Tasks, decisions and notes as events in your git repo. Your team and its coding agents read the same record. MIT, $0, no server, no network.
|
85 % |
|
Home - graph.storage
|
84 % |
|
Regent | Version-Control for AI coding agents
Re_gent | Git for your AI agent’s actions. Undo, trace, and control every step.
|
84 % |
|
Bounded Systems — a checkpoint in front of your coding agent
Your coding agent runs with your access. Bounded Systems puts one checkpoint in front of every privileged action: it checks who is asking and what they're al...
|
84 % |
|
gmonk — An undo button for AI agents
gmonk is a self-hosted safety and disaster-recovery layer for AI agents. It records every action an agent takes — database writes, files, shell commands, obj...
|
84 % |
|
Ataris - The Tracing Layer for Autonomous Agents
Ataris is the tracing layer for autonomous agents. Reconstruct exactly what an agent saw, decided, accessed, and did, and know what data, systems, and creden...
|
84 % |
|
aviary — a zero-dependency kernel for autonomous agents
A zero-dependency ES-module kernel for composing autonomous agents. Written, reviewed and merged entirely by AI agents, live and in public.
|
84 % |
|
ag - elementics | Persistent AI Coding Agent
ag is a persistent AI coding agent with memory. Agents that remember beat agents that re-learn. Checkpoints, result refs, zero dependencies, any model.
|
83 % |
|
Berry — task tracking where the assignee can be a person or a coding agent
Berry is an open-source, MIT-licensed developer workspace where humans and AI coding agents share the same tasks, statuses, reviews and history. Every agent...
|
83 % |
|
Brain — AI agents that build software
Brain is an open-source desktop app where AI agents coordinate autonomously to build software. Add a project, set a goal, agents do the rest.
|
83 % |
|
Uday Kumar · AI systems and data platform engineering
I build and operate the systems behind production AI: agent observability, deterministic agent control, edge inference, and the data platforms under them. GM...
|
83 % |
|
Magen — AI agents you can actually trust in production
We build custom AI agents with cryptographic proof, deterministic policies, human approval gates, and one-click rollback. Powered by Enact.
|
83 % |
|
Code for Agents · Make your codebase a place agents can work
AI coding agents fail in codebases built only for humans. Learn what agent-legible code looks like and how to get there.
|
83 % |
Detected social media networks