Catch intent conflicts between parallel coding agents
Foremerge is the open-source coordination protocol for coding agents, built above Git. Task: Foremerge is the open-source coordination protocol for coding agents, built above Git. Agents keep isolated worktrees while sharing intent, semantic claims, dependencies, provisional ChangeSets, decisions, validation, and provenance. Status: Foremerge 0.6.0 is a pre-1.0, local-first MVP. The CLI, JSON API, MCP server, SQLite store, deterministic conflict detector, and verification-gated lifecycle are implemented. Public schemas may still change. Published benchmark results do not yet exist, and coordination between machines is outside this project's scope. How it works Say you have two AI agents working on the same project at the same time. Each one gets its own copy of the code, so they never fight over files. Both finish. Both look correct. Then you find they undid each other's work. Git cannot warn you about that, because Git compares text and not intent. It will stop you when two agents edit the same part of the same file. What it cannot see is two edits that are each perfectly reasonable on their own and land in different files. If one agent moves every caller onto a new StripePaymentService while another adds PayPal support to the old PaymentService, nothing overlaps, so Git merges both without complaint and the PayPal work is left stranded on a class nothing calls any more. Foremerge fixes this by having agents announce what they are about to do, before they do it. Each agent says what it is about to touch. Not the code, just the target, like "I am going to change the sendEmail function." Every agent reads from one shared list. It is a small database inside your project's .git folder, so every agent on your machine sees the same picture, whether it is Claude, Codex, or Cursor. If two plans collide, you hear about it right away. Foremerge names the two agents, explains why their plans clash, and suggests how to split the work. Both worktrees are still clean at that point, so no work has to be thrown away. Think of it as a shared whiteboard. Before an agent starts, it writes down what it is about to work on, and it reads what everyone else already wrote. Two things Foremerge deliberately does not do. It never locks a file or blocks an agent, because a single crashed agent would then stall the whole fleet, so the warnings are advisory and you stay in charge. And it never asks a model to judge conflicts, so the same inputs always produce the same answer. The conflict Git cannot see yet These agents can work in different trees without touching the same line. The plans still collide: one removes the extension point while the other depends on it. Both agents declare the same symbol:PaymentService scope, one saying it will replace it and the other that it will extend it. Foremerge compares those two declarations before either writes code, raises a HIGH advisory, and suggests coordinating on a stable abstraction such as PaymentProvider. That suggestion is explainable evidence, not an automatic architecture decision or a hard lock. Because the operation is declared rather than read out of the summary, it does not matter how either agent phrased its plan. "Consolidate payments onto Stripe" and "Replace PaymentService with Stripe" reach the same verdict. Git remains the durable repository. Foremerge supplies the missing shared awareness above it. Rendered from the actual conflict fields captured by the 0.1.0 release-binary run in examples/terminal-session.txt. The displayed command uses the shown jq filter; output is abridged for readability. Quickstart: first conflict in under five minutes Let your coding agent do it Paste this into Claude Code, Codex, or Cursor from inside the repository you want to coordinate: Adjust step 4 to whatever this repository's real test command is. Step 3 asks the client to enable an MCP server, so it will prompt you before doing so. The Codex registration is user level, but one registration serves every repository: start Codex inside the repository you want it to coordinate. Or do it yourself You need a recent Git and jq. Install a prebuilt, checksum-verified release binary (macOS and Linux; the script installs to ~/.local/bin): Tip Two commands, one program. This installs foremerge and fmg, the same binary under a shorter name, so fmg status and foremerge status do the same thing. Examples below spell out foremerge; type whichever you prefer.; tools: Claude Code, Codex, Cursor. Human role: The original post does not say how a person stayed involved.; limitations: Foremerge 0.6.0 is a local-first MVP; cross-machine coordination is out of scope. Public schemas may change. It does not replace code review, CI, or security scanning. Conflict detection is heuristic and may miss synonymous concepts or warn on compatible work. Validation proves only that a recorded command passed for a specific fingerprint, not that the test plan was complete. Users must read the full limitations and trust model before using it as an integration gate..
Tools
Published on Agent Work Atlas:
Overview
Foremerge is the open-source coordination protocol for coding agents, built above Git.
Workflow
Foremerge is the open-source coordination protocol for coding agents, built above Git. Agents keep isolated worktrees while sharing intent, semantic claims, dependencies, provisional ChangeSets, decisions, validation, and provenance. Status: Foremerge 0.6.0 is a pre-1.0, local-first MVP. The CLI, JSON API, MCP server, SQLite store, deterministic conflict detector, and verification-gated lifecycle are implemented. Public schemas may still change. Published benchmark results do not yet exist, and coordination between machines is outside this project's scope. How it works Say you have two AI agents working on the same project at the same time. Each one gets its own copy of the code, so they never fight over files. Both finish. Both look correct. Then you find they undid each other's work. Git cannot warn you about that, because Git compares text and not intent. It will stop you when two agents edit the same part of the same file. What it cannot see is two edits that are each perfectly reasonable on their own and land in different files. If one agent moves every caller onto a new StripePaymentService while another adds PayPal support to the old PaymentService, nothing overlaps, so Git merges both without complaint and the PayPal work is left stranded on a class nothing calls any more. Foremerge fixes this by having agents announce what they are about to do, before they do it. Each agent says what it is about to touch. Not the code, just the target, like "I am going to change the sendEmail function." Every agent reads from one shared list. It is a small database inside your project's .git folder, so every agent on your machine sees the same picture, whether it is Claude, Codex, or Cursor. If two plans collide, you hear about it right away. Foremerge names the two agents, explains why their plans clash, and suggests how to split the work. Both worktrees are still clean at that point, so no work has to be thrown away. Think of it as a shared whiteboard. Before an agent starts, it writes down what it is about to work on, and it reads what everyone else already wrote. Two things Foremerge deliberately does not do. It never locks a file or blocks an agent, because a single crashed agent would then stall the whole fleet, so the warnings are advisory and you stay in charge. And it never asks a model to judge conflicts, so the same inputs always produce the same answer. The conflict Git cannot see yet These agents can work in different trees without touching the same line. The plans still collide: one removes the extension point while the other depends on it. Both agents declare the same symbol:PaymentService scope, one saying it will replace it and the other that it will extend it. Foremerge compares those two declarations before either writes code, raises a HIGH advisory, and suggests coordinating on a stable abstraction such as PaymentProvider. That suggestion is explainable evidence, not an automatic architecture decision or a hard lock. Because the operation is declared rather than read out of the summary, it does not matter how either agent phrased its plan. "Consolidate payments onto Stripe" and "Replace PaymentService with Stripe" reach the same verdict. Git remains the durable repository. Foremerge supplies the missing shared awareness above it. Rendered from the actual conflict fields captured by the 0.1.0 release-binary run in examples/terminal-session.txt. The displayed command uses the shown jq filter; output is abridged for readability. Quickstart: first conflict in under five minutes Let your coding agent do it Paste this into Claude Code, Codex, or Cursor from inside the repository you want to coordinate: Adjust step 4 to whatever this repository's real test command is. Step 3 asks the client to enable an MCP server, so it will prompt you before doing so. The Codex registration is user level, but one registration serves every repository: start Codex inside the repository you want it to coordinate. Or do it yourself You need a recent Git and jq. Install a prebuilt, checksum-verified release binary (macOS and Linux; the script installs to ~/.local/bin): Tip Two commands, one program. This installs foremerge and fmg, the same binary under a shorter name, so fmg status and foremerge status do the same thing. Examples below spell out foremerge; type whichever you prefer.
Reported result
No measured business outcomes or benchmark results are published. The tool provides deterministic conflict detection for semantic overlaps (e.g., replacing vs. extending a symbol) that Git text comparison misses. Success is defined by the agent's ability to detect and advise on conflicts before code is written, but actual impact on development speed or error reduction is unverified.
Human role
The original post does not say how a person stayed involved.
Limitations
Foremerge 0.6.0 is a local-first MVP; cross-machine coordination is out of scope. Public schemas may change. It does not replace code review, CI, or security scanning. Conflict detection is heuristic and may miss synonymous concepts or warn on compatible work. Validation proves only that a recorded command passed for a specific fingerprint, not that the test plan was complete. Users must read the full limitations and trust model before using it as an integration gate.
Try it
I want to test Foremerge 0.6.0 on my local repository [replaceable: repo_path] to detect intent conflicts between two simulated coding agents. First, install Foremerge using `curl -fsSL https://foremerge.com/install.sh | sh` and initialize it with `foremerge init`. Register two agents named 'stripe-agent' and 'paypal-agent' using `foremerge --json agent register --name <name> --no-worktree`. Publish an intent for 'stripe-agent' to replace `symbol:PaymentService` and another for 'paypal-agent' to extend the same symbol. Capture the JSON output to verify that a HIGH severity conflict advisory is generated. Do not proceed to actual code changes. If the conflict is detected, record the assessment using `foremerge assess record`. If installation fails or the conflict is not detected, stop and report the error logs. I will manually review the advisory output before considering the test successful.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.