paragma 0.1.3-rc.1 → 0.1.3
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.
- package/README.md +16 -11
- package/bin/pg-darwin-arm64 +0 -0
- package/bin/pg-darwin-x64 +0 -0
- package/bin/pg-linux-arm64 +0 -0
- package/bin/pg-linux-x64 +0 -0
- package/bin/pg-win32-arm64.exe +0 -0
- package/bin/pg-win32-x64.exe +0 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -23,18 +23,18 @@ Paragma answers in one step:
|
|
|
23
23
|
|
|
24
24
|
## Results
|
|
25
25
|
|
|
26
|
-
The same knowledge reached two ways: as plain Markdown notes the agent reads with its own tools, or through Paragma.
|
|
26
|
+
The same knowledge reached two ways: as plain Markdown notes the agent reads with its own tools, or through Paragma. Real agents, OpenCode with two free models (DeepSeek V4.1 Flash and GLM-5.3 Flash, both at their highest reasoning effort), each run in a fresh copy of a small Go project with a memory of 1,539 notes:
|
|
27
27
|
|
|
28
|
-
|
|
|
28
|
+
| Tasks | Access | Result | Tool calls | Tokens processed | Time |
|
|
29
29
|
| --- | --- | --- | --- | --- | --- |
|
|
30
|
-
|
|
|
31
|
-
|
|
|
32
|
-
|
|
|
33
|
-
|
|
|
30
|
+
| 5 questions from memory, 2 models | plain notes | 33/34 facts | 85 | 0.79M | 684 s |
|
|
31
|
+
| | **Paragma** | 33/34 facts | **24** | **0.27M** | 772 s |
|
|
32
|
+
| 3 coding tasks, 2 models | plain notes | 28/28 hidden tests | 267 | 4.94M | 2,673 s |
|
|
33
|
+
| | **Paragma** | 28/28 hidden tests | **213** | **2.40M** | **2,115 s** |
|
|
34
34
|
|
|
35
|
-
Both
|
|
35
|
+
Both ways were equally correct. With Paragma the agents processed about a third of the tokens on questions and half on coding tasks, with fewer tool calls; Paragma was the cheaper of the two in 15 of 16 paired runs.
|
|
36
36
|
|
|
37
|
-
|
|
37
|
+
The coding tasks are a recurring error whose obvious fix is wrong, a feature finished in a second conversation that only knows what the first one recorded, and a change governed by project rules. Without memory, agents failed parts of each in earlier runs. Each task ran once per model and condition, so read the ratios as a trend. Earlier runs, including Antigravity with Gemini, are in [bench/RESULTS.md](bench/RESULTS.md).
|
|
38
38
|
|
|
39
39
|
## Install
|
|
40
40
|
|
|
@@ -65,7 +65,7 @@ pg setup
|
|
|
65
65
|
| Antigravity | CLI, IDE | `~/.gemini/AGENTS.md` | `AGENTS.md` in its folder |
|
|
66
66
|
| OpenCode | CLI | `~/.config/opencode/AGENTS.md` | `AGENTS.md` in its folder |
|
|
67
67
|
|
|
68
|
-
The
|
|
68
|
+
The results above were measured with OpenCode, earlier ones with Antigravity. In scripts: `pg setup codex --global` or `pg setup claude --dir .`
|
|
69
69
|
|
|
70
70
|
## What the agent does with it
|
|
71
71
|
|
|
@@ -73,18 +73,23 @@ The agent learns these commands from the section `pg setup` writes; `pg help` li
|
|
|
73
73
|
|
|
74
74
|
```bash
|
|
75
75
|
pg prime # start of a conversation: what memory holds
|
|
76
|
+
pg start payments --goal "Card payments" --step "Webhook" --step "Tests" --decision "Discount before VAT"
|
|
77
|
+
pg tree # the code: files, their declarations, the rules and errors about each
|
|
78
|
+
pg related payments/refund.go # before changing a file: its rules, decisions, past fixes, last commits
|
|
76
79
|
pg context "refund" # rules, decisions and fixes on a topic, in one call
|
|
77
80
|
pg run -- go test ./... # on failure: the known fix; on success: rules for the files you changed
|
|
78
|
-
pg start payments --goal "Card payments" --step "Webhook" --step "Tests" --decision "Discount before VAT"
|
|
79
81
|
pg done t2f4 # mark a step done; prints the next one in full
|
|
82
|
+
pg checkpoint "where it stands" # before stopping: a handoff for the next conversation
|
|
80
83
|
pg resume payments # in a new conversation: goal, decisions, open steps, changed code
|
|
81
84
|
pg error record --from-last --cause "CRLF checkout" --fix "Normalise line endings before hashing"
|
|
82
85
|
```
|
|
83
86
|
|
|
87
|
+
`pg start` on a project that exists continues it. `pg related` without a path lists the files you changed with the rules that apply to them. Notes, folders and whole projects are renamed or moved with `pg mv`, and many `pg` calls can run at once.
|
|
88
|
+
|
|
84
89
|
## How it works
|
|
85
90
|
|
|
86
91
|
- **Spaces and projects.** Notes are plain Markdown in `~/.paragma/Spaces/<space>/<project>/`. A space works like an Obsidian vault: search and links stay inside it. Open the folder in any editor.
|
|
87
|
-
- **One index.** A SQLite full-text index next to the notes is updated on every call and can be deleted at any time.
|
|
92
|
+
- **One index.** A SQLite full-text index next to the notes is updated on every call and can be deleted at any time. Parallel calls wait for each other's writes instead of failing.
|
|
88
93
|
- **Addresses.** Every result starts with an address the agent can pass back: `shopkit/rules^r003`, `payments/payments#Decisions`, `shopkit/errors/catalog-checksum-crlf`.
|
|
89
94
|
- **Local.** Paragma never opens a network connection. Memory stays on your computer and out of git.
|
|
90
95
|
|
package/bin/pg-darwin-arm64
CHANGED
|
Binary file
|
package/bin/pg-darwin-x64
CHANGED
|
Binary file
|
package/bin/pg-linux-arm64
CHANGED
|
Binary file
|
package/bin/pg-linux-x64
CHANGED
|
Binary file
|
package/bin/pg-win32-arm64.exe
CHANGED
|
Binary file
|
package/bin/pg-win32-x64.exe
CHANGED
|
Binary file
|