Skip to content

Commit 41d4b70

Browse files
Claudeclaude
authored andcommitted
chore: migrate repository references from nTEG-dev to gitmem-dev
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1 parent 6ba6f0d commit 41d4b70

7 files changed

Lines changed: 246 additions & 11 deletions

File tree

CHANGELOG.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -141,7 +141,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
141141
- Cache management (status, flush, health)
142142
- Agent identity detection
143143

144-
[Unreleased]: https://github.com/nTEG-dev/gitmem/compare/v1.0.0...HEAD
145-
[1.0.0]: https://github.com/nTEG-dev/gitmem/compare/v0.2.0...v1.0.0
146-
[0.2.0]: https://github.com/nTEG-dev/gitmem/compare/v0.1.0...v0.2.0
147-
[0.1.0]: https://github.com/nTEG-dev/gitmem/releases/tag/v0.1.0
144+
[Unreleased]: https://github.com/gitmem-dev/gitmem/compare/v1.0.0...HEAD
145+
[1.0.0]: https://github.com/gitmem-dev/gitmem/compare/v0.2.0...v1.0.0
146+
[0.2.0]: https://github.com/gitmem-dev/gitmem/compare/v0.1.0...v0.2.0
147+
[0.1.0]: https://github.com/gitmem-dev/gitmem/releases/tag/v0.1.0

CONTRIBUTING.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@ Thanks for your interest in contributing to GitMem! This guide covers developmen
1212
### Getting Started
1313

1414
```bash
15-
git clone https://github.com/nTEG-dev/gitmem.git
15+
git clone https://github.com/gitmem-dev/gitmem.git
1616
cd gitmem
1717
npm install
1818
npm run build

README.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,8 +5,8 @@
55
<p align="center">
66
<a href="https://www.npmjs.com/package/gitmem-mcp"><img src="https://img.shields.io/npm/v/gitmem-mcp?style=flat-square&color=ed1e25&label=npm" alt="npm version" /></a>
77
<a href="https://www.npmjs.com/package/gitmem-mcp"><img src="https://img.shields.io/npm/dm/gitmem-mcp?style=flat-square&color=333333&label=downloads" alt="npm downloads" /></a>
8-
<a href="https://github.com/nTEG-dev/gitmem/blob/main/LICENSE"><img src="https://img.shields.io/github/license/nTEG-dev/gitmem?style=flat-square&color=ed1e25" alt="MIT License" /></a>
9-
<a href="https://github.com/nTEG-dev/gitmem/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/nTEG-dev/gitmem/ci.yml?style=flat-square&color=333333&label=build" alt="Build" /></a>
8+
<a href="https://github.com/gitmem-dev/gitmem/blob/main/LICENSE"><img src="https://img.shields.io/github/license/gitmem-dev/gitmem?style=flat-square&color=ed1e25" alt="MIT License" /></a>
9+
<a href="https://github.com/gitmem-dev/gitmem/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/gitmem-dev/gitmem/ci.yml?style=flat-square&color=333333&label=build" alt="Build" /></a>
1010
<img src="https://img.shields.io/badge/node-%3E%3D22-ed1e25?style=flat-square" alt="Node.js >= 22" />
1111
</p>
1212

@@ -149,7 +149,7 @@ Your AI agent likely has its own memory file (MEMORY.md, .cursorrules, etc.). He
149149
## Development
150150

151151
```bash
152-
git clone https://github.com/nTEG-dev/gitmem.git
152+
git clone https://github.com/gitmem-dev/gitmem.git
153153
cd gitmem
154154
npm install
155155
npm run build

distribution/openclaw/LISTING.md

Lines changed: 90 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,90 @@
1+
# OpenClaw Directory Listing — gitmem
2+
3+
## Submission Target
4+
https://openclawdir.com → "Submit Skill" (requires Google sign-in)
5+
6+
## Listing Fields
7+
8+
**Name:** `gitmem`
9+
10+
**Tagline / Short Description:**
11+
Institutional memory for AI agents. Your agent stops repeating the same mistakes.
12+
13+
**Full Description:**
14+
GitMem is an MCP server that gives your agent persistent memory across sessions — not chat history, but earned knowledge. It tracks mistakes (scars), successes (wins), architectural decisions, and unfinished work so your agent learns from experience instead of starting from scratch every time. Complements OpenClaw's built-in memory by adding institutional knowledge on top of conversational context.
15+
16+
**Category:** Memory / Productivity / Developer Tools
17+
18+
**Tags:** `memory`, `mcp`, `institutional-memory`, `session-management`, `learning`, `scars`, `decisions`
19+
20+
**Homepage:** https://gitmem.ai
21+
22+
**Repository:** https://github.com/gitmem-dev/gitmem
23+
24+
**npm:** https://www.npmjs.com/package/gitmem-mcp
25+
26+
**Install command:**
27+
```bash
28+
openclaw mcp add gitmem -- npx -y gitmem-mcp
29+
```
30+
31+
---
32+
33+
## Submission Checklist
34+
35+
- [ ] Sign in to openclawdir.com with Google
36+
- [ ] Go to "Submit Skill"
37+
- [ ] Upload or paste SKILL.md content
38+
- [ ] Verify fields auto-populate from frontmatter
39+
- [ ] Submit — AI review runs automatically
40+
- [ ] If approved, listing goes live immediately
41+
42+
## Post-Listing Promotion
43+
44+
### OpenClaw Discord
45+
Post in #skills or #show-and-tell:
46+
47+
> **gitmem — institutional memory for your agent**
48+
>
49+
> Your agent forgets everything between sessions. gitmem fixes that.
50+
>
51+
> It's an MCP server that tracks mistakes (scars), wins, decisions, and open threads — so your agent learns from experience. Not chat history — earned lessons.
52+
>
53+
> `openclaw mcp add gitmem -- npx -y gitmem-mcp`
54+
>
55+
> Works alongside OpenClaw's built-in memory. It handles conversational context; gitmem handles institutional knowledge.
56+
>
57+
> https://gitmem.ai | https://github.com/gitmem-dev/gitmem
58+
59+
### GitHub awesome-openclaw-skills
60+
PR to https://github.com/VoltAgent/awesome-openclaw-skills adding gitmem under "Memory" category.
61+
62+
### X / Twitter
63+
Draft tweet (see /tweet skill or post manually):
64+
65+
> Your AI agent makes the same mistakes every session because it starts from zero.
66+
>
67+
> gitmem gives it institutional memory — scars from past failures, wins from what worked, decisions with rationale.
68+
>
69+
> Now available as an OpenClaw skill.
70+
>
71+
> openclaw mcp add gitmem -- npx -y gitmem-mcp
72+
>
73+
> https://gitmem.ai
74+
75+
## Differentiation Talking Points
76+
77+
When the community asks "how is this different from OpenClaw memory?":
78+
79+
1. **OpenClaw memory = what was said.** GitMem = what was learned.
80+
2. **OpenClaw persists conversations.** GitMem persists lessons.
81+
3. **OpenClaw recalls context.** GitMem recalls warnings before you act.
82+
4. **They're complementary.** Use both. OpenClaw remembers you like Python; GitMem remembers you got burned by Python 2/3 migration last week.
83+
84+
When asked "how is this different from triple-memory?":
85+
86+
1. **triple-memory is broad recall** — LanceDB vectors, git-notes, file search
87+
2. **gitmem is opinionated workflow** — recall → confirm → work → reflect → close
88+
3. **Scars have counter-arguments** — not just "don't do X" but "here's why you might ignore this"
89+
4. **Session ceremonies** — structured reflection captures what broke, what worked, what to do differently
90+
5. **Threads** — unfinished work carries across sessions automatically

distribution/openclaw/SKILL.md

Lines changed: 145 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,145 @@
1+
---
2+
name: gitmem
3+
description: Institutional memory for AI agents via MCP. Gives your agent persistent memory that survives across sessions — mistakes (scars), successes (wins), decisions, and open threads. Use when you want your agent to stop repeating the same mistakes, carry context between sessions, and learn from experience. Not chat history — earned knowledge.
4+
homepage: https://gitmem.ai
5+
metadata: '{"openclaw":{"emoji":"🧠","requires":{"bins":["npx"],"env":[]},"os":["darwin","linux","win32"]}}'
6+
user-invocable: true
7+
---
8+
9+
# GitMem — Institutional Memory for AI Agents
10+
11+
Your agent starts from zero every session. GitMem fixes that.
12+
13+
It's an MCP server that gives your agent **persistent memory across sessions** — not chat history, but *earned knowledge*: mistakes to avoid, approaches that worked, architectural decisions, and unfinished work.
14+
15+
## Setup
16+
17+
### 1. Add the MCP server
18+
19+
```bash
20+
openclaw mcp add gitmem -- npx -y gitmem-mcp
21+
```
22+
23+
Or add manually to `~/.openclaw/mcp.json`:
24+
25+
```json
26+
{
27+
"mcpServers": {
28+
"gitmem": {
29+
"command": "npx",
30+
"args": ["-y", "gitmem-mcp"]
31+
}
32+
}
33+
}
34+
```
35+
36+
### 2. Initialize in your project
37+
38+
```bash
39+
cd your-project
40+
npx gitmem-mcp init
41+
```
42+
43+
The wizard creates:
44+
- `.gitmem/` directory with 3 starter scars
45+
- Memory protocol instructions for your agent
46+
- Lifecycle hooks for automatic session management
47+
48+
Already have config? The wizard merges without destroying anything. Re-running is safe.
49+
50+
## How It Works
51+
52+
```
53+
recall → work → learn → close → recall → ...
54+
```
55+
56+
1. **Recall** — Before acting, the agent checks memory for relevant lessons
57+
2. **Work** — The agent applies past lessons automatically
58+
3. **Learn** — Mistakes become scars, successes become wins
59+
4. **Close** — Session reflection persists context for next time
60+
61+
## What Gets Remembered
62+
63+
| Type | Purpose | Example |
64+
|------|---------|---------|
65+
| **Scars** | Mistakes to avoid | "Always validate UUID format before DB lookup" |
66+
| **Wins** | Approaches that worked | "Parallel agent spawning cut review time by 60%" |
67+
| **Patterns** | Reusable strategies | "5-tier test pyramid for MCP servers" |
68+
| **Decisions** | Architectural choices + rationale | "Chose JWT over session cookies for stateless auth" |
69+
| **Threads** | Unfinished work across sessions | "Rate limiting still needs implementation" |
70+
71+
Every scar includes **counter-arguments** — reasons why someone might reasonably ignore it. This prevents memory from becoming rigid rules.
72+
73+
## Tools Reference
74+
75+
Once the MCP server is running, your agent gets these tools:
76+
77+
| Tool | When to use |
78+
|------|-------------|
79+
| `recall` | Before any task — surfaces relevant warnings from past experience |
80+
| `confirm_scars` | After recall — acknowledge each scar as APPLYING, N_A, or REFUTED |
81+
| `search` | Explore institutional knowledge by topic |
82+
| `log` | Browse recent learnings chronologically |
83+
| `session_start` | Beginning of session — loads context and open threads |
84+
| `session_close` | End of session — persists what you learned |
85+
| `create_learning` | Capture a mistake (scar), success (win), or pattern |
86+
| `create_decision` | Log an architectural or operational decision |
87+
| `list_threads` | See unresolved work carrying over between sessions |
88+
| `create_thread` | Track something that needs follow-up later |
89+
90+
## How This Differs from OpenClaw's Built-in Memory
91+
92+
OpenClaw's native memory tracks **what was said** — conversation history, user preferences, context.
93+
94+
GitMem tracks **what was learned** — earned lessons from things that broke, decisions and their rationale, approaches that worked and why. It's the difference between remembering a conversation and remembering the lesson from it.
95+
96+
They complement each other:
97+
98+
| | OpenClaw Memory | GitMem |
99+
|---|----------------|--------|
100+
| **Scope** | Conversational context | Institutional knowledge |
101+
| **Loaded** | Automatically every turn | On-demand via recall |
102+
| **Best for** | Preferences, history | Lessons, decisions, patterns |
103+
| **Updates** | Continuous | Session ceremonies |
104+
| **Example** | "User prefers Python" | "Always run migrations with --dry-run first" |
105+
106+
## Example Session
107+
108+
```
109+
Agent: [session_start] Loading context...
110+
2 open threads, 15 scars in memory.
111+
112+
You: "Add caching to the API"
113+
114+
Agent: [recall plan="implement caching layer"]
115+
⚠ Scar: "Cache invalidation caused stale data bug — always set TTL"
116+
⚠ Scar: "Redis connection pooling required in containerized deploys"
117+
[confirm_scars] APPLYING both — using TTL and connection pool.
118+
119+
... implements caching with TTL and pooling ...
120+
121+
You: "done for today"
122+
123+
Agent: [session_close]
124+
Reflection:
125+
- What worked: Redis caching with TTL pattern
126+
- New scar: "Cache key collisions between services — namespace keys"
127+
- Open thread: "Cache warming strategy still TBD"
128+
```
129+
130+
## CLI Commands
131+
132+
| Command | Description |
133+
|---------|-------------|
134+
| `npx gitmem-mcp init` | Interactive setup wizard |
135+
| `npx gitmem-mcp init --yes` | Non-interactive setup |
136+
| `npx gitmem-mcp init --dry-run` | Preview changes |
137+
| `npx gitmem-mcp check` | Diagnostic health check |
138+
| `npx gitmem-mcp uninstall` | Clean removal (preserves data) |
139+
140+
## Links
141+
142+
- **Docs**: https://gitmem.ai/docs
143+
- **npm**: https://www.npmjs.com/package/gitmem-mcp
144+
- **GitHub**: https://github.com/gitmem-dev/gitmem
145+
- **Getting Started**: https://gitmem.ai/docs/getting-started

package.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -72,7 +72,7 @@
7272
"license": "MIT",
7373
"repository": {
7474
"type": "git",
75-
"url": "https://github.com/nTEG-dev/gitmem.git"
75+
"url": "https://github.com/gitmem-dev/gitmem.git"
7676
},
7777
"homepage": "https://gitmem.ai",
7878
"publishConfig": {

tests/e2e/organic-discovery/analysis/blog-draft-organic-discovery.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ The answer turns out to depend on something more interesting than we anticipated
88

99
## The Setup
1010

11-
We built a test harness for [GitMem](https://github.com/nTEG-dev/gitmem), our open-source persistent memory system for AI coding agents. GitMem gives agents institutional memory — the ability to record what they've learned, recall relevant lessons before acting, and carry context across sessions.
11+
We built a test harness for [GitMem](https://github.com/gitmem-dev/gitmem), our open-source persistent memory system for AI coding agents. GitMem gives agents institutional memory — the ability to record what they've learned, recall relevant lessons before acting, and carry context across sessions.
1212

1313
The experiment measured four adoption behaviors:
1414
- **Discovery**: Did the agent find and invoke gitmem tools?
@@ -91,6 +91,6 @@ We're continuing to explore what drives this transition. The v4 nudge's emphasis
9191

9292
## The Data
9393

94-
All results are from the [GitMem organic discovery test harness](https://github.com/nTEG-dev/gitmem), which uses the Claude Agent SDK to run controlled multi-session experiments. The full dataset — 62 result files with per-session tool call logs, MEMORY.md diffs, and aggregate metrics — is available in the repository.
94+
All results are from the [GitMem organic discovery test harness](https://github.com/gitmem-dev/gitmem), which uses the Claude Agent SDK to run controlled multi-session experiments. The full dataset — 62 result files with per-session tool call logs, MEMORY.md diffs, and aggregate metrics — is available in the repository.
9595

9696
The test harness itself is open source. If you're building tools for AI agents and want to measure organic adoption rather than just integration tests, the framework might be useful.

0 commit comments

Comments
 (0)