agent-chat-plugin 0.1.0__tar.gz → 0.2.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,201 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright 2026 n24q02m
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.
@@ -0,0 +1,145 @@
1
+ Metadata-Version: 2.4
2
+ Name: agent-chat-plugin
3
+ Version: 0.2.0
4
+ Summary: Peer AI agents coordinate through markdown messages in shared channel folders — no orchestrator, autonomous zero-token waiting, cross-platform.
5
+ Author: n24q02m
6
+ License: Apache-2.0
7
+ Project-URL: Homepage, https://github.com/n24q02m/agent-chat-plugin
8
+ Project-URL: Specification, https://github.com/n24q02m/agent-chat-plugin/blob/main/SPEC.md
9
+ Keywords: multi-agent,coordination,markdown,blackboard,claude-code,agent-skills,peer-to-peer
10
+ Classifier: Programming Language :: Python :: 3
11
+ Classifier: License :: OSI Approved :: Apache Software License
12
+ Classifier: Operating System :: OS Independent
13
+ Classifier: Topic :: Software Development :: Libraries
14
+ Requires-Python: >=3.8
15
+ Description-Content-Type: text/markdown
16
+ License-File: LICENSE
17
+ Dynamic: license-file
18
+
19
+ # agent-chat
20
+
21
+ [![PyPI](https://img.shields.io/pypi/v/agent-chat-plugin.svg)](https://pypi.org/project/agent-chat-plugin/)
22
+ [![Python](https://img.shields.io/pypi/pyversions/agent-chat-plugin.svg)](https://pypi.org/project/agent-chat-plugin/)
23
+ [![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
24
+ [![CI](https://github.com/n24q02m/agent-chat-plugin/actions/workflows/ci.yml/badge.svg)](https://github.com/n24q02m/agent-chat-plugin/actions/workflows/ci.yml)
25
+
26
+ <!-- BEGIN: AUTO-GENERATED-CROSS-PROMO -->
27
+ <details>
28
+ <summary><strong>Sister projects from n24q02m</strong> (click to expand)</summary>
29
+
30
+ | Project | Tagline | Tag |
31
+ |---|---|---|
32
+ | [agent-chat-plugin](https://github.com/n24q02m/agent-chat-plugin) | Peer AI agents chat in a shared folder — no human relay, no orchestrator, wor... | Tooling |
33
+ | [better-code-review-graph](https://github.com/n24q02m/better-code-review-graph) | Knowledge graph for token-efficient code reviews -- semantic search and call-... | MCP |
34
+ | [better-drive](https://github.com/n24q02m/better-drive) | 2-way Google Drive sync with .driveignore filter — rclone engine, Windows tray | Tooling |
35
+ | [better-email-mcp](https://github.com/n24q02m/better-email-mcp) | IMAP/SMTP email for AI agents -- read, send, organize folders, and manage att... | MCP |
36
+ | [better-godot-mcp](https://github.com/n24q02m/better-godot-mcp) | Composite MCP server for Godot Engine -- 17 composite tools for AI-assisted g... | MCP |
37
+ | [better-notion-mcp](https://github.com/n24q02m/better-notion-mcp) | Markdown-first Notion for AI agents -- pages, databases, blocks, and comments... | MCP |
38
+ | [better-semantic-release](https://github.com/n24q02m/better-semantic-release) | Drop-in python-semantic-release fork with built-in release-safety guards (orp... | Tooling |
39
+ | [better-telegram-mcp](https://github.com/n24q02m/better-telegram-mcp) | Telegram for AI agents -- messages, chats, media, and contacts across both bo... | MCP |
40
+ | [better-workspace-mcp](https://github.com/n24q02m/better-workspace-mcp) | Google Workspace MCP server (Docs/Drive/Calendar/Gmail/Sheets/Slides/Tasks/Ch... | MCP |
41
+ | [claude-plugins](https://github.com/n24q02m/claude-plugins) | Claude Code plugin marketplace for the n24q02m MCP servers -- install web sea... | Marketplace |
42
+ | [imagine-mcp](https://github.com/n24q02m/imagine-mcp) | Image and video understanding + generation for AI agents -- across Gemini, Op... | MCP |
43
+ | [jules-task-archiver](https://github.com/n24q02m/jules-task-archiver) | Chrome Extension for bulk operations on Jules tasks via batchexecute API -- a... | Tooling |
44
+ | [mcp-core](https://github.com/n24q02m/mcp-core) | Shared foundation for building MCP servers -- Streamable HTTP transport, OAut... | MCP |
45
+ | [mnemo-mcp](https://github.com/n24q02m/mnemo-mcp) | Persistent AI memory with hybrid search and embedded sync. Open, free, unlimi... | MCP |
46
+ | [qwen3-embed](https://github.com/n24q02m/qwen3-embed) | Lightweight Qwen3 text embedding and reranking via ONNX Runtime and GGUF | Library |
47
+ | [skret](https://github.com/n24q02m/skret) | Secrets without the server. | CLI |
48
+ | [tacet](https://github.com/n24q02m/tacet) | A self-distilling neuro-symbolic cascade that amortises LLM cost across knowl... | Tooling |
49
+ | [web-core](https://github.com/n24q02m/web-core) | Shared web infrastructure package for search, scraping, HTTP security, and st... | Library |
50
+ | [wet-mcp](https://github.com/n24q02m/wet-mcp) | Open-source MCP server for AI agents: web search, content extraction, and lib... | MCP |
51
+
52
+ </details>
53
+ <!-- END: AUTO-GENERATED-CROSS-PROMO -->
54
+
55
+
56
+ **Peer AI agents chat in a shared folder — no human relay, no orchestrator, works on
57
+ Windows, waits at zero tokens.**
58
+
59
+ Multiple agent sessions (Claude Code, Codex, Cursor, OpenCode — same tool or mixed)
60
+ coordinate as equals by exchanging markdown messages in shared **channel folders**.
61
+ The folder is the whole state: git-committable, human-readable, replayable. A crashed
62
+ session loses nothing.
63
+
64
+ One dependency-free file (`chat.py`, Python stdlib) runs identically on Windows, WSL,
65
+ and Linux. Waiting for a reply blocks in-process — **an agent that is waiting spends
66
+ zero model tokens.**
67
+
68
+ > Distributed as **`agent-chat-plugin`** on PyPI and as a Claude Code plugin (the short
69
+ > name `agent-chat` was taken on PyPI). The command and skill are still `agent-chat`.
70
+
71
+ ## Why this exists
72
+
73
+ Claude Code now has a native **cross-session messaging** path for Claude Code sessions
74
+ on supported platforms. The peer case this project targets is broader: N equal sessions
75
+ across Claude Code, Codex, Cursor, OpenCode, or mixed tools coordinating through a
76
+ file-backed, auditable folder of messages and autonomously waiting on each other. This
77
+ is that cross-tool answer. (Honest scope: this is a young space; see `COMPARISON.md` for
78
+ the native Claude Code overlap and the exact differences.)
79
+
80
+ ### Claude Code native overlap
81
+
82
+ Claude Code `v2.1.224+` provides **Cross-session messaging** through `ListAgents` and
83
+ `SendMessage` on macOS/Linux, including WSL2; native Windows is not currently supported.
84
+ That feature is Claude-Code-only and delivers messages directly between sessions. This
85
+ project remains distinct through mixed-tool coordination, native Windows support,
86
+ Markdown channels that are git-committable and replayable, atomic claims/cursors, and
87
+ zero-token in-process waiting. On supported Claude Code platforms, the native path may
88
+ make this plugin's optional unread-notification hooks redundant; it does not replace the
89
+ file-backed protocol.
90
+
91
+ ## Quickstart
92
+
93
+ ```bash
94
+ # a channel = a group chat
95
+ python chat.py init review --members alice,bob --topic "code review"
96
+
97
+ # alice posts to bob
98
+ python chat.py post review --from alice --to bob --title "Schema v0.2" --body-file msg.md
99
+
100
+ # bob reads what's new for him (only messages addressed to him or the group)
101
+ python chat.py read review --as bob
102
+
103
+ # alice waits for bob's reply — burns 0 tokens while blocked
104
+ python chat.py wait review --as alice --timeout 900
105
+ ```
106
+
107
+ Root defaults to `~/agent-chat`; override with `$AGENT_CHAT_ROOT` or `--root`. Run
108
+ `python chat.py <cmd> --help` for all flags.
109
+
110
+ ## How it works
111
+
112
+ - **Channels** — one folder per group chat; make as many as you need (`init`).
113
+ - **Messages** — `NNNN-<from>-<slug>.md` with frontmatter (`from`, `to`, `reply_to`,
114
+ `status`, `title`). `to: all` broadcasts.
115
+ - **Cursors** — `read`/`wait` show only what's new for you and never re-scan the thread.
116
+ - **Atomic** — sequence numbers are allocated under a lock (no duplicate `-11`); task
117
+ claiming uses atomic rename (lose the race -> move on).
118
+
119
+ Six rules keep peers from stepping on each other: one channel per topic; claim before
120
+ you act; message don't chatter; `wait` don't poll-with-the-model; read since your
121
+ cursor; reply in a new file. Full protocol in `SPEC.md`.
122
+
123
+ ## Two modes, two budgets
124
+
125
+ - **Live swarm** — N sessions running concurrently, `wait`-ing on each other. Buys
126
+ wall-clock parallelism + fault tolerance; costs more tokens. For abundant budgets.
127
+ - **Async handoff / audit** — post a summary when a session ends; the next session
128
+ reads it. Nearly free — usable on a tight budget.
129
+
130
+ ## Install & distribution
131
+
132
+ - **As a CLI** — `pipx install agent-chat-plugin` then run `agent-chat`
133
+ (or `uvx --from agent-chat-plugin agent-chat`).
134
+ - **As a skill** — drop `SKILL.md` + `chat.py` into your agent's skills directory;
135
+ works across tools that read the Agent Skills / `SKILL.md` standard.
136
+ - **As a Claude Code plugin** — via a plugin marketplace.
137
+
138
+ ## Status
139
+
140
+ Early (v0). The reference implementation is tested end-to-end; the protocol may still
141
+ change. Feedback and interop with `tap` / `TICK.md` welcome.
142
+
143
+ ## License
144
+
145
+ Apache-2.0.
@@ -0,0 +1,127 @@
1
+ # agent-chat
2
+
3
+ [![PyPI](https://img.shields.io/pypi/v/agent-chat-plugin.svg)](https://pypi.org/project/agent-chat-plugin/)
4
+ [![Python](https://img.shields.io/pypi/pyversions/agent-chat-plugin.svg)](https://pypi.org/project/agent-chat-plugin/)
5
+ [![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
6
+ [![CI](https://github.com/n24q02m/agent-chat-plugin/actions/workflows/ci.yml/badge.svg)](https://github.com/n24q02m/agent-chat-plugin/actions/workflows/ci.yml)
7
+
8
+ <!-- BEGIN: AUTO-GENERATED-CROSS-PROMO -->
9
+ <details>
10
+ <summary><strong>Sister projects from n24q02m</strong> (click to expand)</summary>
11
+
12
+ | Project | Tagline | Tag |
13
+ |---|---|---|
14
+ | [agent-chat-plugin](https://github.com/n24q02m/agent-chat-plugin) | Peer AI agents chat in a shared folder — no human relay, no orchestrator, wor... | Tooling |
15
+ | [better-code-review-graph](https://github.com/n24q02m/better-code-review-graph) | Knowledge graph for token-efficient code reviews -- semantic search and call-... | MCP |
16
+ | [better-drive](https://github.com/n24q02m/better-drive) | 2-way Google Drive sync with .driveignore filter — rclone engine, Windows tray | Tooling |
17
+ | [better-email-mcp](https://github.com/n24q02m/better-email-mcp) | IMAP/SMTP email for AI agents -- read, send, organize folders, and manage att... | MCP |
18
+ | [better-godot-mcp](https://github.com/n24q02m/better-godot-mcp) | Composite MCP server for Godot Engine -- 17 composite tools for AI-assisted g... | MCP |
19
+ | [better-notion-mcp](https://github.com/n24q02m/better-notion-mcp) | Markdown-first Notion for AI agents -- pages, databases, blocks, and comments... | MCP |
20
+ | [better-semantic-release](https://github.com/n24q02m/better-semantic-release) | Drop-in python-semantic-release fork with built-in release-safety guards (orp... | Tooling |
21
+ | [better-telegram-mcp](https://github.com/n24q02m/better-telegram-mcp) | Telegram for AI agents -- messages, chats, media, and contacts across both bo... | MCP |
22
+ | [better-workspace-mcp](https://github.com/n24q02m/better-workspace-mcp) | Google Workspace MCP server (Docs/Drive/Calendar/Gmail/Sheets/Slides/Tasks/Ch... | MCP |
23
+ | [claude-plugins](https://github.com/n24q02m/claude-plugins) | Claude Code plugin marketplace for the n24q02m MCP servers -- install web sea... | Marketplace |
24
+ | [imagine-mcp](https://github.com/n24q02m/imagine-mcp) | Image and video understanding + generation for AI agents -- across Gemini, Op... | MCP |
25
+ | [jules-task-archiver](https://github.com/n24q02m/jules-task-archiver) | Chrome Extension for bulk operations on Jules tasks via batchexecute API -- a... | Tooling |
26
+ | [mcp-core](https://github.com/n24q02m/mcp-core) | Shared foundation for building MCP servers -- Streamable HTTP transport, OAut... | MCP |
27
+ | [mnemo-mcp](https://github.com/n24q02m/mnemo-mcp) | Persistent AI memory with hybrid search and embedded sync. Open, free, unlimi... | MCP |
28
+ | [qwen3-embed](https://github.com/n24q02m/qwen3-embed) | Lightweight Qwen3 text embedding and reranking via ONNX Runtime and GGUF | Library |
29
+ | [skret](https://github.com/n24q02m/skret) | Secrets without the server. | CLI |
30
+ | [tacet](https://github.com/n24q02m/tacet) | A self-distilling neuro-symbolic cascade that amortises LLM cost across knowl... | Tooling |
31
+ | [web-core](https://github.com/n24q02m/web-core) | Shared web infrastructure package for search, scraping, HTTP security, and st... | Library |
32
+ | [wet-mcp](https://github.com/n24q02m/wet-mcp) | Open-source MCP server for AI agents: web search, content extraction, and lib... | MCP |
33
+
34
+ </details>
35
+ <!-- END: AUTO-GENERATED-CROSS-PROMO -->
36
+
37
+
38
+ **Peer AI agents chat in a shared folder — no human relay, no orchestrator, works on
39
+ Windows, waits at zero tokens.**
40
+
41
+ Multiple agent sessions (Claude Code, Codex, Cursor, OpenCode — same tool or mixed)
42
+ coordinate as equals by exchanging markdown messages in shared **channel folders**.
43
+ The folder is the whole state: git-committable, human-readable, replayable. A crashed
44
+ session loses nothing.
45
+
46
+ One dependency-free file (`chat.py`, Python stdlib) runs identically on Windows, WSL,
47
+ and Linux. Waiting for a reply blocks in-process — **an agent that is waiting spends
48
+ zero model tokens.**
49
+
50
+ > Distributed as **`agent-chat-plugin`** on PyPI and as a Claude Code plugin (the short
51
+ > name `agent-chat` was taken on PyPI). The command and skill are still `agent-chat`.
52
+
53
+ ## Why this exists
54
+
55
+ Claude Code now has a native **cross-session messaging** path for Claude Code sessions
56
+ on supported platforms. The peer case this project targets is broader: N equal sessions
57
+ across Claude Code, Codex, Cursor, OpenCode, or mixed tools coordinating through a
58
+ file-backed, auditable folder of messages and autonomously waiting on each other. This
59
+ is that cross-tool answer. (Honest scope: this is a young space; see `COMPARISON.md` for
60
+ the native Claude Code overlap and the exact differences.)
61
+
62
+ ### Claude Code native overlap
63
+
64
+ Claude Code `v2.1.224+` provides **Cross-session messaging** through `ListAgents` and
65
+ `SendMessage` on macOS/Linux, including WSL2; native Windows is not currently supported.
66
+ That feature is Claude-Code-only and delivers messages directly between sessions. This
67
+ project remains distinct through mixed-tool coordination, native Windows support,
68
+ Markdown channels that are git-committable and replayable, atomic claims/cursors, and
69
+ zero-token in-process waiting. On supported Claude Code platforms, the native path may
70
+ make this plugin's optional unread-notification hooks redundant; it does not replace the
71
+ file-backed protocol.
72
+
73
+ ## Quickstart
74
+
75
+ ```bash
76
+ # a channel = a group chat
77
+ python chat.py init review --members alice,bob --topic "code review"
78
+
79
+ # alice posts to bob
80
+ python chat.py post review --from alice --to bob --title "Schema v0.2" --body-file msg.md
81
+
82
+ # bob reads what's new for him (only messages addressed to him or the group)
83
+ python chat.py read review --as bob
84
+
85
+ # alice waits for bob's reply — burns 0 tokens while blocked
86
+ python chat.py wait review --as alice --timeout 900
87
+ ```
88
+
89
+ Root defaults to `~/agent-chat`; override with `$AGENT_CHAT_ROOT` or `--root`. Run
90
+ `python chat.py <cmd> --help` for all flags.
91
+
92
+ ## How it works
93
+
94
+ - **Channels** — one folder per group chat; make as many as you need (`init`).
95
+ - **Messages** — `NNNN-<from>-<slug>.md` with frontmatter (`from`, `to`, `reply_to`,
96
+ `status`, `title`). `to: all` broadcasts.
97
+ - **Cursors** — `read`/`wait` show only what's new for you and never re-scan the thread.
98
+ - **Atomic** — sequence numbers are allocated under a lock (no duplicate `-11`); task
99
+ claiming uses atomic rename (lose the race -> move on).
100
+
101
+ Six rules keep peers from stepping on each other: one channel per topic; claim before
102
+ you act; message don't chatter; `wait` don't poll-with-the-model; read since your
103
+ cursor; reply in a new file. Full protocol in `SPEC.md`.
104
+
105
+ ## Two modes, two budgets
106
+
107
+ - **Live swarm** — N sessions running concurrently, `wait`-ing on each other. Buys
108
+ wall-clock parallelism + fault tolerance; costs more tokens. For abundant budgets.
109
+ - **Async handoff / audit** — post a summary when a session ends; the next session
110
+ reads it. Nearly free — usable on a tight budget.
111
+
112
+ ## Install & distribution
113
+
114
+ - **As a CLI** — `pipx install agent-chat-plugin` then run `agent-chat`
115
+ (or `uvx --from agent-chat-plugin agent-chat`).
116
+ - **As a skill** — drop `SKILL.md` + `chat.py` into your agent's skills directory;
117
+ works across tools that read the Agent Skills / `SKILL.md` standard.
118
+ - **As a Claude Code plugin** — via a plugin marketplace.
119
+
120
+ ## Status
121
+
122
+ Early (v0). The reference implementation is tested end-to-end; the protocol may still
123
+ change. Feedback and interop with `tap` / `TICK.md` welcome.
124
+
125
+ ## License
126
+
127
+ Apache-2.0.
@@ -0,0 +1,145 @@
1
+ Metadata-Version: 2.4
2
+ Name: agent-chat-plugin
3
+ Version: 0.2.0
4
+ Summary: Peer AI agents coordinate through markdown messages in shared channel folders — no orchestrator, autonomous zero-token waiting, cross-platform.
5
+ Author: n24q02m
6
+ License: Apache-2.0
7
+ Project-URL: Homepage, https://github.com/n24q02m/agent-chat-plugin
8
+ Project-URL: Specification, https://github.com/n24q02m/agent-chat-plugin/blob/main/SPEC.md
9
+ Keywords: multi-agent,coordination,markdown,blackboard,claude-code,agent-skills,peer-to-peer
10
+ Classifier: Programming Language :: Python :: 3
11
+ Classifier: License :: OSI Approved :: Apache Software License
12
+ Classifier: Operating System :: OS Independent
13
+ Classifier: Topic :: Software Development :: Libraries
14
+ Requires-Python: >=3.8
15
+ Description-Content-Type: text/markdown
16
+ License-File: LICENSE
17
+ Dynamic: license-file
18
+
19
+ # agent-chat
20
+
21
+ [![PyPI](https://img.shields.io/pypi/v/agent-chat-plugin.svg)](https://pypi.org/project/agent-chat-plugin/)
22
+ [![Python](https://img.shields.io/pypi/pyversions/agent-chat-plugin.svg)](https://pypi.org/project/agent-chat-plugin/)
23
+ [![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
24
+ [![CI](https://github.com/n24q02m/agent-chat-plugin/actions/workflows/ci.yml/badge.svg)](https://github.com/n24q02m/agent-chat-plugin/actions/workflows/ci.yml)
25
+
26
+ <!-- BEGIN: AUTO-GENERATED-CROSS-PROMO -->
27
+ <details>
28
+ <summary><strong>Sister projects from n24q02m</strong> (click to expand)</summary>
29
+
30
+ | Project | Tagline | Tag |
31
+ |---|---|---|
32
+ | [agent-chat-plugin](https://github.com/n24q02m/agent-chat-plugin) | Peer AI agents chat in a shared folder — no human relay, no orchestrator, wor... | Tooling |
33
+ | [better-code-review-graph](https://github.com/n24q02m/better-code-review-graph) | Knowledge graph for token-efficient code reviews -- semantic search and call-... | MCP |
34
+ | [better-drive](https://github.com/n24q02m/better-drive) | 2-way Google Drive sync with .driveignore filter — rclone engine, Windows tray | Tooling |
35
+ | [better-email-mcp](https://github.com/n24q02m/better-email-mcp) | IMAP/SMTP email for AI agents -- read, send, organize folders, and manage att... | MCP |
36
+ | [better-godot-mcp](https://github.com/n24q02m/better-godot-mcp) | Composite MCP server for Godot Engine -- 17 composite tools for AI-assisted g... | MCP |
37
+ | [better-notion-mcp](https://github.com/n24q02m/better-notion-mcp) | Markdown-first Notion for AI agents -- pages, databases, blocks, and comments... | MCP |
38
+ | [better-semantic-release](https://github.com/n24q02m/better-semantic-release) | Drop-in python-semantic-release fork with built-in release-safety guards (orp... | Tooling |
39
+ | [better-telegram-mcp](https://github.com/n24q02m/better-telegram-mcp) | Telegram for AI agents -- messages, chats, media, and contacts across both bo... | MCP |
40
+ | [better-workspace-mcp](https://github.com/n24q02m/better-workspace-mcp) | Google Workspace MCP server (Docs/Drive/Calendar/Gmail/Sheets/Slides/Tasks/Ch... | MCP |
41
+ | [claude-plugins](https://github.com/n24q02m/claude-plugins) | Claude Code plugin marketplace for the n24q02m MCP servers -- install web sea... | Marketplace |
42
+ | [imagine-mcp](https://github.com/n24q02m/imagine-mcp) | Image and video understanding + generation for AI agents -- across Gemini, Op... | MCP |
43
+ | [jules-task-archiver](https://github.com/n24q02m/jules-task-archiver) | Chrome Extension for bulk operations on Jules tasks via batchexecute API -- a... | Tooling |
44
+ | [mcp-core](https://github.com/n24q02m/mcp-core) | Shared foundation for building MCP servers -- Streamable HTTP transport, OAut... | MCP |
45
+ | [mnemo-mcp](https://github.com/n24q02m/mnemo-mcp) | Persistent AI memory with hybrid search and embedded sync. Open, free, unlimi... | MCP |
46
+ | [qwen3-embed](https://github.com/n24q02m/qwen3-embed) | Lightweight Qwen3 text embedding and reranking via ONNX Runtime and GGUF | Library |
47
+ | [skret](https://github.com/n24q02m/skret) | Secrets without the server. | CLI |
48
+ | [tacet](https://github.com/n24q02m/tacet) | A self-distilling neuro-symbolic cascade that amortises LLM cost across knowl... | Tooling |
49
+ | [web-core](https://github.com/n24q02m/web-core) | Shared web infrastructure package for search, scraping, HTTP security, and st... | Library |
50
+ | [wet-mcp](https://github.com/n24q02m/wet-mcp) | Open-source MCP server for AI agents: web search, content extraction, and lib... | MCP |
51
+
52
+ </details>
53
+ <!-- END: AUTO-GENERATED-CROSS-PROMO -->
54
+
55
+
56
+ **Peer AI agents chat in a shared folder — no human relay, no orchestrator, works on
57
+ Windows, waits at zero tokens.**
58
+
59
+ Multiple agent sessions (Claude Code, Codex, Cursor, OpenCode — same tool or mixed)
60
+ coordinate as equals by exchanging markdown messages in shared **channel folders**.
61
+ The folder is the whole state: git-committable, human-readable, replayable. A crashed
62
+ session loses nothing.
63
+
64
+ One dependency-free file (`chat.py`, Python stdlib) runs identically on Windows, WSL,
65
+ and Linux. Waiting for a reply blocks in-process — **an agent that is waiting spends
66
+ zero model tokens.**
67
+
68
+ > Distributed as **`agent-chat-plugin`** on PyPI and as a Claude Code plugin (the short
69
+ > name `agent-chat` was taken on PyPI). The command and skill are still `agent-chat`.
70
+
71
+ ## Why this exists
72
+
73
+ Claude Code now has a native **cross-session messaging** path for Claude Code sessions
74
+ on supported platforms. The peer case this project targets is broader: N equal sessions
75
+ across Claude Code, Codex, Cursor, OpenCode, or mixed tools coordinating through a
76
+ file-backed, auditable folder of messages and autonomously waiting on each other. This
77
+ is that cross-tool answer. (Honest scope: this is a young space; see `COMPARISON.md` for
78
+ the native Claude Code overlap and the exact differences.)
79
+
80
+ ### Claude Code native overlap
81
+
82
+ Claude Code `v2.1.224+` provides **Cross-session messaging** through `ListAgents` and
83
+ `SendMessage` on macOS/Linux, including WSL2; native Windows is not currently supported.
84
+ That feature is Claude-Code-only and delivers messages directly between sessions. This
85
+ project remains distinct through mixed-tool coordination, native Windows support,
86
+ Markdown channels that are git-committable and replayable, atomic claims/cursors, and
87
+ zero-token in-process waiting. On supported Claude Code platforms, the native path may
88
+ make this plugin's optional unread-notification hooks redundant; it does not replace the
89
+ file-backed protocol.
90
+
91
+ ## Quickstart
92
+
93
+ ```bash
94
+ # a channel = a group chat
95
+ python chat.py init review --members alice,bob --topic "code review"
96
+
97
+ # alice posts to bob
98
+ python chat.py post review --from alice --to bob --title "Schema v0.2" --body-file msg.md
99
+
100
+ # bob reads what's new for him (only messages addressed to him or the group)
101
+ python chat.py read review --as bob
102
+
103
+ # alice waits for bob's reply — burns 0 tokens while blocked
104
+ python chat.py wait review --as alice --timeout 900
105
+ ```
106
+
107
+ Root defaults to `~/agent-chat`; override with `$AGENT_CHAT_ROOT` or `--root`. Run
108
+ `python chat.py <cmd> --help` for all flags.
109
+
110
+ ## How it works
111
+
112
+ - **Channels** — one folder per group chat; make as many as you need (`init`).
113
+ - **Messages** — `NNNN-<from>-<slug>.md` with frontmatter (`from`, `to`, `reply_to`,
114
+ `status`, `title`). `to: all` broadcasts.
115
+ - **Cursors** — `read`/`wait` show only what's new for you and never re-scan the thread.
116
+ - **Atomic** — sequence numbers are allocated under a lock (no duplicate `-11`); task
117
+ claiming uses atomic rename (lose the race -> move on).
118
+
119
+ Six rules keep peers from stepping on each other: one channel per topic; claim before
120
+ you act; message don't chatter; `wait` don't poll-with-the-model; read since your
121
+ cursor; reply in a new file. Full protocol in `SPEC.md`.
122
+
123
+ ## Two modes, two budgets
124
+
125
+ - **Live swarm** — N sessions running concurrently, `wait`-ing on each other. Buys
126
+ wall-clock parallelism + fault tolerance; costs more tokens. For abundant budgets.
127
+ - **Async handoff / audit** — post a summary when a session ends; the next session
128
+ reads it. Nearly free — usable on a tight budget.
129
+
130
+ ## Install & distribution
131
+
132
+ - **As a CLI** — `pipx install agent-chat-plugin` then run `agent-chat`
133
+ (or `uvx --from agent-chat-plugin agent-chat`).
134
+ - **As a skill** — drop `SKILL.md` + `chat.py` into your agent's skills directory;
135
+ works across tools that read the Agent Skills / `SKILL.md` standard.
136
+ - **As a Claude Code plugin** — via a plugin marketplace.
137
+
138
+ ## Status
139
+
140
+ Early (v0). The reference implementation is tested end-to-end; the protocol may still
141
+ change. Feedback and interop with `tap` / `TICK.md` welcome.
142
+
143
+ ## License
144
+
145
+ Apache-2.0.
@@ -6,4 +6,6 @@ agent_chat_plugin.egg-info/PKG-INFO
6
6
  agent_chat_plugin.egg-info/SOURCES.txt
7
7
  agent_chat_plugin.egg-info/dependency_links.txt
8
8
  agent_chat_plugin.egg-info/entry_points.txt
9
- agent_chat_plugin.egg-info/top_level.txt
9
+ agent_chat_plugin.egg-info/top_level.txt
10
+ tests/test_chat.py
11
+ tests/test_hooks.py