All comparisons
Shared session memory
Concord vs Mosaic
Mosaic records what your agents did. Concord coordinates what they're doing now, before two of them do the same thing.
Concord
- Yes14
- Partly0
- Not in their docs0
Mosaic
- Yes3
- Partly1
- Not in their docs10
Across 14 capabilities, from public docs as of October 2026.
at a glance
Two tools, side by side.
| Attribute | Concord | Mosaic |
|---|---|---|
| What it is | Shared work-state and messaging for coding agents (MCP server + CLI) | Shared memory of AI coding sessions across a team |
| Works with | Claude Code, Codex, Cursor, Gemini CLI, Copilot CLI, Grok Build, Goose, Antigravity, Devin CLI, any MCP client | Claude Code, Codex, Cursor and others |
| Runs | Inside the agents you already use. Local SQLite, or Cloud across machines | CLI and app that sync sessions |
| License | MIT | Not open source |
| Price | Free locally. Cloud free for one person. Team $15/seat, agents free | Not public |
feature by feature
Concord 14 of 14. Mosaic 3.
| Capability | Concord | Mosaic |
|---|---|---|
| Works with the agents you already run | Yes9 harnesses + any MCP client | Yes |
| Native MCP server | Yes | Not in their docs |
| Claim files before editing | Yes | Not in their docs |
| Overlap warning before an edit | Yes | Not in their docs |
| Block edits to claimed files in hooks or CI | Yesconcord check | Not in their docs |
| Replyable prompts between different vendors' agents | Yeslive where the harness allows | Not in their docs |
| Task memory: decisions, assumptions, findings | Yes | Yessession history |
| Accepted handoffs with an audit trail | Yesversioned, append-only | Not in their docs |
| Review packet: tests, risks, provenance | Yes | Not in their docs |
| Flags work a dead session left claimed | Yes | Not in their docs |
| Agents on different machines | YesConcord Cloud | Yes |
| Open source | YesMIT | Not in their docs |
| Runs locally with no account | Yes | Not in their docs |
| Keep your terminal and IDE, no new app | Yes | Partly |
From Mosaic's public docs as of October 2026.YesPartlyNot in their docs
why teams pick concord
Session history is useful hindsight. Concord gives your agents shared memory and live coordination in one MCP server.
- 01
Before, not after
A record of a collision doesn't undo it. Claims and overlap warnings stop it happening.
Stop overwrites - 02
Memory agents can use
Decisions and assumptions are typed and on the task, ready for the next agent to read.
Persist decisions - 03
Open source
MIT, local-first, no account. Cloud only when you need several machines.
How it works
common questions
- Is Concord a Mosaic alternative?
- Yes. Concord keeps decisions, assumptions and findings on each task, and adds live claims, overlap warnings and messages between agents.
- Does Concord store my code or transcripts?
- No. Concord stores the task state agents write to it. Its telemetry never includes code, paths, task content or messages.
- Can a new agent pick up where another stopped?
- Yes. The task's intent, decisions and findings stay in the workspace, and transfer_work hands ownership over explicitly.
keep reading