You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
<imgsrc="https://raw.githubusercontent.com/Sankhya-AI/Dhee/main/docs/dhee-hero.png"alt="The shared learning layer for AI agents"width="100%">
2
+
<imgsrc="https://raw.githubusercontent.com/Sankhya-AI/Dhee/main/docs/dhee-hero.png"alt="Dhee world memory layer for AI agents"width="100%">
3
3
</p>
4
4
5
5
<h1align="center">Dhee</h1>
6
6
7
7
<palign="center">
8
-
<b>The local developer brain for AI coding agents.</b><br>
9
-
Persistent memory, repo cognition, handoff, routing, and proof for Codex, Claude Code, Cursor, Gemini CLI, Cline, and any MCP client.
8
+
<b>World memory for AI agents.</b><br>
9
+
A context compiler, repo brain, narrative scene graph, handoff bus, and proof layer for Codex, Claude Code, Cursor, Gemini CLI, Cline, Chotu, and any MCP client.
10
10
</p>
11
11
12
12
<palign="center">
@@ -18,19 +18,11 @@
18
18
19
19
---
20
20
21
-
## What Dhee Is
21
+
Dhee gives an agent the bigger story before it takes the next action.
22
22
23
-
Dhee is a production-ready, local-first context and memory layer for coding agents.
23
+
LLMs are powerful, but they still miss the arc. What is the user trying to become? What happened last session? Which decision was already made? Which failure should not be repeated? Which proof is required before touching code?
24
24
25
-
It is not a model, not an autocomplete tool, and not a hosted vector database. It sits beside your agent and keeps the work grounded:
26
-
27
-
-**Memory that does not rot into noise:** canonical facts, preferences, decisions, project rules, passive evidence, test fixtures, and operational events are separated.
28
-
-**Repo cognition that survives sessions:** symbol graph, imports, calls, route/component map, test map, ownership, historical failures, and impact analysis.
29
-
-**Context routing:** large files, grep output, logs, test runs, and agent handoffs become compact digests with evidence pointers.
30
-
-**Action contracts:** before edits, Dhee can compile the task into files, constraints, tests, risk, and proof obligations.
31
-
-**Handoff:** another agent can continue with the current repo state, decisions, blockers, and next action.
32
-
33
-
The promise is simple: **less prompt sludge, fewer repeated mistakes, better grounded code edits.**
25
+
Dhee stores that story locally and compiles it into the smallest useful context. Not a transcript pile. Not vibes. Memory with shape.
34
26
35
27
## Install
36
28
@@ -39,13 +31,13 @@ pip install dhee
39
31
dhee install
40
32
```
41
33
42
-
Or use the installer:
34
+
Or use the one-command installer:
43
35
44
36
```bash
45
37
curl -fsSL https://raw.githubusercontent.com/Sankhya-AI/Dhee/main/install.sh | sh
46
38
```
47
39
48
-
Then wire a repo:
40
+
Wire a repo:
49
41
50
42
```bash
51
43
cd /path/to/repo
@@ -54,7 +46,75 @@ dhee status
54
46
dhee ui
55
47
```
56
48
57
-
MCP clients can use:
49
+
## What Is Dhee?
50
+
51
+
Dhee is the memory layer agents should have had from day one.
52
+
53
+
It runs beside the model and answers the questions that raw chat history cannot:
54
+
55
+
| The agent needs | Dhee gives it |
56
+
| --- | --- |
57
+
| What matters right now? | A compiled context packet with included and rejected reasons. |
58
+
| What happened before? | Durable user, project, repo, scene, and handoff memory. |
59
+
| What files are risky? | Repo brain impact analysis, likely tests, owners, routes, and symbols. |
60
+
| What should not be used? | Secret filters, privacy classes, supersession, contradiction, and proof gates. |
61
+
| What is the larger story? | Series, Seasons, Episodes, Scenes, and SceneCards. |
62
+
| Can another agent continue? | Session digests, shared task state, evidence refs, and handoff packets. |
63
+
64
+
## Context Compiler
65
+
66
+
Most agents drown in context or starve without it. Dhee does the boring hard part in the middle.
67
+
68
+
- Reads summarize files instead of dumping them.
69
+
- Searches return compact matches with expansion pointers.
70
+
- Tool output becomes reusable evidence, not one-turn sludge.
71
+
- Task contracts define files, constraints, tests, and proof obligations.
72
+
- SceneCards become the default retrieval object.
73
+
- Raw transcripts stay out of prompts unless explicitly requested.
74
+
75
+
The model gets the part of the world it needs, in the form it can use.
76
+
77
+
## Narrative Memory
78
+
79
+
This is the new Dhee core.
80
+
81
+
```text
82
+
Series -> Season -> Episode -> Scene -> SceneCard -> MemoryItem
83
+
```
84
+
85
+
In plain English:
86
+
87
+
-**Series** is the biggest purpose. Example: become a successful CTO.
88
+
-**Season** is a period of the story: learning, struggle, first success, downfall, comeback.
89
+
-**Episode** is the meaningful arc of a day.
90
+
-**Scene** is a bounded work moment with a hero, intent, action, obstacle, result, and outcome.
91
+
-**SceneCard** is the retrieval card the agent sees later: compact, evidence-backed, privacy-aware.
92
+
-**MemoryItem** is promoted only when the SceneCard is worth keeping long-term.
93
+
94
+
That story gives the model anticipation. The prior is advisory, never bossy: explicit user intent, facts, privacy, and proof gates win.
95
+
96
+
## Retrieval That Actually Ranks
97
+
98
+
Dhee can run model-free, but the production retrieval path is built for serious agent work:
Deterministic filters still go first: secrets, private scenes, contradicted cards, superseded cards, and code-mutation proof gates cannot be talked around by a high similarity score.
114
+
115
+
## MCP Tools
116
+
117
+
Add Dhee to any MCP client:
58
118
59
119
```json
60
120
{
@@ -64,73 +124,63 @@ MCP clients can use:
64
124
}
65
125
```
66
126
67
-
## How It Helps A Coding Agent
127
+
Scene intelligence tools:
128
+
129
+
```text
130
+
dhee_scene_start
131
+
dhee_scene_event
132
+
dhee_scene_end
133
+
dhee_scene_context
134
+
dhee_narrative_prior
135
+
```
136
+
137
+
Core context tools:
68
138
69
-
Without Dhee, every turn is a loose pile of files, logs, stale memory, and guesses.
139
+
```text
140
+
dhee_context_bootstrap
141
+
dhee_read
142
+
dhee_grep
143
+
dhee_bash
144
+
dhee_context_pack
145
+
dhee_scene_search
146
+
```
70
147
71
-
With Dhee, the agent gets a compact working packet:
148
+
A good agent loop is simple:
72
149
73
-
1.**Recall:** relevant user/project memory, current handoff, and repo facts.
Dhee can run model-free for repo tooling and handoff. For high-quality semantic memory, the default provider map points to the NVIDIA-compatible OpenAI API stack used in our LongMemEval runs:
The result is an agent that feels less random because it can see the arc.
134
184
135
185
## Benchmarks
136
186
@@ -142,11 +192,11 @@ On LongMemEval full 500-question recall:
142
192
143
193
Reproduction notes and outputs live in [`benchmarks/longmemeval/`](benchmarks/longmemeval/).
144
194
145
-
## What Is In The Open Source Package
195
+
## What Ships
146
196
147
-
You get the local developer brain: memory OS, repo brain, DheeFS, MCP server, CLI, UI, runtime daemon, handoff bus, update capsules, and release/proof tooling.
197
+
The open source package includes the local memory OS, context compiler, DheeFS, MCP servers, CLI, UI, runtime daemon, handoff bus, repo brain, update capsules, narrative scene intelligence, release checks, and proof tooling.
148
198
149
-
Enterprise/team governance, hosted dashboards, org policy, and managed source connectors can build on top of these local primitives. The OSS package is useful by itself and does not require a hosted account.
199
+
Team governance, hosted dashboards, org policy, and managed source connectors can build on top of these local primitives. Dhee itself is useful without a hosted account.
0 commit comments