Corrections log
Catalog decisions recorded by ADE Index. Removal means the selected product surface is outside our scope; it does not mean the product has shut down.
Berd
The captured product is a general-purpose Goose desktop distribution. The README documents packaging and enterprise seams, but no coding task, code-change review or specific coding-agent coordination workflow. Remove from the ADE directory on this evidence; this is a scope decision, not proof that Goose cannot code.
Flock
Flock is a general visual multi-agent workflow harness with file, shell and browser access. The captured workflow examples do not establish autonomous software implementation or specific coding-agent coordination; generic autonomy is insufficient. Remove from the software-development directory on current evidence.
## 🤝 Multi-Agent Harness & Workflow — Visual Orchestration for AI Agents
Source · read 2026-11-18Flock is more than just a chat client. It's a comprehensive **multi-agent harness** combined with a powerful **Visual Workflow Editor**. It orchestrates and runs AI agents locally or inside sandbox containers to read/write files, execute bash commands, browse the web, and run complex pipelines. You see everything the agent does, and you're always in control.
Source · read 2026-11-18
FrontierAgent
The shipped workflows target research, repository analysis and file deliverables. Repository reading/analysis and generic shell mutation approvals do not establish implementation, code editing or specifically coding-agent coordination. Remove as a general research agent rather than force it into CLI agents.
Jazz
Jazz is documented as an everyday terminal/bot assistant with research, document, git-review and scheduling tools. Its PR-review Action is secondary and generic file/git access does not establish an autonomous code-writing workflow. Remove the general assistant surface rather than labeling its terminal entrypoint a CLI coding agent.
Subsequently reconsidered: current listing.
LettaBot
LettaBot is the deprecated general messaging/persistent-memory assistant, not the separate Letta Code coding-agent surface to which development moved. Generic file/search/command tools do not justify merging that identity with Letta Code. Remove the general assistant listing while preserving any verified lifecycle/redirect treatment.
Your personal AI assistant that remembers everything across **Telegram, Slack, Discord, WhatsApp, and Signal** — plus Bluesky Jetstream feed ingestion. Powered by the [Letta Code SDK](https://github.com/letta-ai/letta-code-sdk).
Source · read 2026-11-18> **LettaBot is no longer actively maintained.** All new development is happening in [Letta Code](https://docs.letta.com/letta-code) via [Channels](https://docs.letta.com/letta-code/channels) and [Remote Environments](https://docs.letta.com/letta-code/remote).
Source · read 2026-11-18
OpenSquilla
OpenSquilla is a general personal-agent/runtime surface with coding among bundled skills. Its reported software-repair benchmark confirms a coding capability, so removal must not claim it cannot code; however the captured product workflow remains general multi-channel assistance/model routing rather than a specifically selected coding-agent development environment. Remove the general surface and reconsider a separately documented coding surface if one is selected.
Subsequently reconsidered: current listing.
A microkernel AI agent for your CLI, Web UI, and chat channels.
Source · read 2026-11-18| **On-demand skills and MCP** | 15 bundled skills (coding, GitHub, cron, pptx/docx/xlsx/pdf, summarization, tmux, weather, and more) load only when the task needs them. The current source includes MCP client and server support; see [MCP setup](docs/mcp-server.md#requirements) for SDK 2.x installation, then run `opensquilla mcp-server run` to expose session workflows to another MCP client. Skills can be authored, installed, and published from the CLI. |
Source · read 2026-11-18350 multilingual SWE-bench-style repair tasks from 8 languages and 43 repositories, with the
Source · read 2026-11-18
openswarm
The current product is a general AI desktop for sales/operations/hiring/research. Apps-on-request is a feature claim, but no developer code-edit/repository/test workflow or specifically coding-agent workforce is documented. Apply the same general-platform boundary used for OtoDock: remove the current non-development product without claiming it cannot generate code or has shut down.
OpenSwarm has moved in a new direction, and its development no longer happens here.
Source · read 2026-11-18OpenSwarm is a desktop where many agents work at once.
Source · read 2026-11-18Hand the repetitive, multi-step work to a swarm, whether you sell, run operations, hire or research.
Source · read 2026-11-18
oto-dock
The documented product is a company-agent platform for general departmental work, chat, schedules and phone calls. Claude Code/Codex are execution engines; their use does not itself establish coding-agent coordination as the selected workflow. App creation is one general-business promise, with no scoped repository/test/PR workflow in this capture. Remove on current product scope rather than treating the engine names as sufficient.
Subsequently reconsidered: current listing.
<h1 align="center">The self-hosted platform for your company's AI agents.</h1>
Source · read 2026-11-18Every agent is a digital employee you give a job. It has its own knowledge,
Source · read 2026-11-18On the server, agents run inside per-session sandboxes as Claude Code or Codex
Source · read 2026-11-18
free-code
Excluded by owner decision: a patched copy of proprietary Claude Code with telemetry disabled and features unlocked; not a qualifying separate implementation under the derivative rule. Source provenance is not established sufficiently to list.
A clean, buildable fork of Anthropic's [Claude Code](https://docs.anthropic.com/en/docs/claude-code) CLI -- the terminal-native AI coding agent. The upstream source became publicly available on March 31, 2026 through a source map exposure in the npm distribution.
Source · read 2026-11-18