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
Copy file name to clipboardExpand all lines: README.md
+18-19Lines changed: 18 additions & 19 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -19,6 +19,24 @@ Created by Jean-Baptiste Thery and published under the JCode Labs npm scope.
19
19
20
20
Built by Jean-Baptiste Thery, freelance full-stack/AI tooling engineer at JCode Labs.
21
21
22
+
## Developer Use Cases
23
+
24
+
Mimir is designed for agent-assisted development when the useful context is local, private, and
25
+
spread across repositories, specifications, exports, and synced folders.
26
+
27
+
| Use case | What it enables |
28
+
| --- | --- |
29
+
| Index a repository's documentation | Ask Claude Code, Codex, Kimi Code CLI, OpenCode, Cline, or another agent to implement features from local README files, architecture notes, API contracts, ADRs, and runbooks. |
30
+
| Code from a specification or `cahier des charges`| Turn a local PRD, tender response, client brief, or engineering spec into an implementation plan, acceptance checklist, and cited change guidance. |
31
+
| Work from a downloaded Google Drive folder | Point Mimir at files synced locally through Google Drive for desktop, then let the agent retrieve context without uploading the corpus to a hosted RAG service. |
32
+
| Onboard to a legacy codebase | Ask where a flow is implemented, which modules own a responsibility, which docs explain a behavior, and what to read before changing risky code. |
33
+
| Keep multiple agents on the same evidence | Install the same project skills and MCP server for Claude Code, Codex, Kimi Code CLI, OpenCode, and Cline so each tool retrieves from the same local index. |
34
+
| Prepare implementation and review work | Generate cited task breakdowns, migration notes, release checklists, QA plans, and code-review context from the same local sources the team uses. |
35
+
| Audit local knowledge coverage | Check which supported files were indexed, which formats were skipped, whether secrets are likely present, and whether golden queries still retrieve expected evidence. |
36
+
37
+
The workflow stays simple: keep files on disk, run `mimir ingest`, connect your coding agent through
38
+
MCP or portable skills, then ask it to work from cited local passages.
39
+
22
40
## At A Glance
23
41
24
42
Mimir is the local evidence layer for AI agents: put documents in a repository, index them locally,
@@ -173,25 +191,6 @@ Mimir is not a hosted SaaS, not a remote vector database, and not a certified hi
173
191
For regulated or state-grade environments, pair it with encrypted disks, controlled machines,
174
192
release verification, and an external security review.
175
193
176
-
## Use Cases
177
-
178
-
Mimir is useful whenever source material should stay local but an AI agent still needs grounded
179
-
context.
180
-
181
-
| Use case | Example questions |
182
-
| --- | --- |
183
-
| Understand a code repository | "Where is authentication implemented?", "What depends on this module?", "Summarize the payment flow." |
184
-
| Understand architecture | "What services exist?", "What are the data boundaries?", "Which components are risky to change?" |
185
-
| Analyze specifications | "What does the technical spec require?", "Which requirements are still unclear?", "Generate an implementation checklist." |
186
-
| Work through a request for proposal or tender | "What are the mandatory constraints?", "Which documents prove compliance?", "What risks should be clarified?" |
187
-
| Study courses and training material | "Summarize chapter three.", "Create revision questions.", "Compare these two concepts." |
188
-
| Analyze a book or long report | "Extract the main thesis.", "Find recurring arguments.", "Create a chapter-by-chapter brief." |
189
-
| Build an internal knowledge base | "What is the policy for incident review?", "Who owns this process?", "Which source says that?" |
190
-
| Prepare meetings or decisions | "Give me a one-page briefing.", "What is missing before deciding?", "List action items and evidence." |
191
-
| Ask questions over offline documents | "Which files mention local-only operation?", "What evidence supports this claim?" |
192
-
| Generate audio briefings | "Create a listenable high-quality or offline summary of the current dossier." |
193
-
| Generate Markdown reports | "Write a cited local report with findings, risks, next actions, and sources." |
0 commit comments