github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14844] Feature Request: Add Octomind Integration to ollama launch #56089

New Issue
Open
opened 2026-04-29 10:15:05 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 10:15:05 -05:00
Owner
Copy Link

Originally created by @donhardman on GitHub (Mar 14, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14844

Summary

Add Octomind as a new integration for ollama launch. Octomind is a session-based AI development assistant written in Rust with MCP support and native Ollama provider support.

What is Octomind?

Repository: https://github.com/muvon/octomind
Website: https://muvon.io
License: Apache 2.0

Features:

  • 7 LLM providers including native Ollama support (ollama:model-name)
  • MCP Protocol Support - Full Model Context Protocol implementation
  • Session-based workflow - Persistent context across conversations
  • Plan-first architecture - Multi-step planning with validation
  • Built-in tools - Shell, file editing, code search (ast_grep), web browsing
  • Native binary - Written in Rust, no Node.js required

Native Ollama Support

Octomind already has native Ollama provider support:

# ~/.config/octomind/config.toml
model = "ollama:qwen3-coder"

[providers.ollama]
# Uses OLLAMA_API_KEY or defaults to localhost

Environment variable: OLLAMA_API_KEY (already documented in Octomind)

Why Add Octomind?

Feature Octomind Other Tools
Provider-agnostic ✅ 7 providers Single provider
MCP native ✅ Built-in Varies
Runtime Native binary Node.js
Sessions ✅ Persistent Varies
Cost tracking ✅ Built-in Varies

Proposed Implementation

cmd/launch/octomind.go

package launch

import (
	"fmt"
	"os"
	"os/exec"
	"path/filepath"

	"github.com/ollama/ollama/cmd/internal/fileutil"
	"github.com/ollama/ollama/envconfig"
)

type Octomind struct{}

func (o *Octomind) String() string { return "Octomind" }

func (o *Octomind) Run(model string, args []string) error {
	if _, err := exec.LookPath("octomind"); err != nil {
		return fmt.Errorf("octomind is not installed, install from https://muvon.io")
	}
	cmd := exec.Command("octomind", "session")
	cmd.Stdin = os.Stdin
	cmd.Stdout = os.Stdout
	cmd.Stderr = os.Stderr
	cmd.Env = append(os.Environ(),
		"OLLAMA_API_KEY=ollama",
	)
	return cmd.Run()
}

func (o *Octomind) Paths() []string {
	home, err := os.UserHomeDir()
	if err != nil {
		return nil
	}
	p := filepath.Join(home, ".config", "octomind", "config.toml")
	if _, err := os.Stat(p); err == nil {
		return []string{p}
	}
	return nil
}

func (o *Octomind) Edit(models []string) error {
	if len(models) == 0 {
		return nil
	}
	home, err := os.UserHomeDir()
	if err != nil {
		return err
	}
	configDir := filepath.Join(home, ".config", "octomind")
	configPath := filepath.Join(configDir, "config.toml")
	if err := os.MkdirAll(configDir, 0o755); err != nil {
		return err
	}

	// Octomind uses TOML with model = "provider:model" format
	config := fmt.Sprintf(`# Generated by ollama launch
model = "ollama:%s"

[providers.ollama]
base_url = "%s/v1"
`, models[0], envconfig.Host().String())

	return fileutil.WriteWithBackup(configPath, []byte(config))
}

func (o *Octomind) Models() []string {
	home, err := os.UserHomeDir()
	if err != nil {
		return nil
	}
	configPath := filepath.Join(home, ".config", "octomind", "config.toml")
	data, err := os.ReadFile(configPath)
	if err != nil {
		return nil
	}
	// Parse model = "ollama:model_name"
	content := string(data)
	// Simple extraction - look for ollama: prefix
	for _, line := range strings.Split(content, "\n") {
		if strings.HasPrefix(line, `model = "ollama:`) {
			model := strings.TrimPrefix(line, `model = "ollama:`)
			model = strings.TrimSuffix(model, `"`)
			return []string{model}
		}
	}
	return nil
}

Registry Entry (cmd/launch/registry.go)

Add to integrationSpecs:

{
	Name: "octomind",
	Runner: &Octomind{},
	Description: "Session-based AI development assistant with MCP support",
	Install: IntegrationInstallSpec{
		CheckInstalled: func() bool {
			_, err := exec.LookPath("octomind")
			return err == nil
		},
		URL: "https://muvon.io",
	},
},

User Experience

# Launch Octomind with Ollama
ollama launch octomind

# With specific model
ollama launch octomind --model qwen3-coder

# Configure without launching
ollama launch octomind --config

Installation

Users install Octomind via:

curl -fsSL https://raw.githubusercontent.com/muvon/octomind/master/install.sh | bash
# or
cargo install octomind

Ready for PR

I have the implementation ready. Will submit PR after discussion.

Octomind already listed in:

  • awesome-mcp-clients
  • awesome-ai-devtools
  • awesome-ai-coding-tools
  • awesome-cli-rust
Originally created by @donhardman on GitHub (Mar 14, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14844 ## Summary Add **Octomind** as a new integration for `ollama launch`. Octomind is a session-based AI development assistant written in Rust with MCP support and **native Ollama provider support**. ## What is Octomind? **Repository**: https://github.com/muvon/octomind **Website**: https://muvon.io **License**: Apache 2.0 Features: - **7 LLM providers** including native Ollama support (`ollama:model-name`) - **MCP Protocol Support** - Full Model Context Protocol implementation - **Session-based workflow** - Persistent context across conversations - **Plan-first architecture** - Multi-step planning with validation - **Built-in tools** - Shell, file editing, code search (ast_grep), web browsing - **Native binary** - Written in Rust, no Node.js required ## Native Ollama Support Octomind already has native Ollama provider support: ```toml # ~/.config/octomind/config.toml model = "ollama:qwen3-coder" [providers.ollama] # Uses OLLAMA_API_KEY or defaults to localhost ``` Environment variable: `OLLAMA_API_KEY` (already documented in Octomind) ## Why Add Octomind? | Feature | Octomind | Other Tools | |---------|----------|-------------| | Provider-agnostic | ✅ 7 providers | Single provider | | MCP native | ✅ Built-in | Varies | | Runtime | Native binary | Node.js | | Sessions | ✅ Persistent | Varies | | Cost tracking | ✅ Built-in | Varies | ## Proposed Implementation ### `cmd/launch/octomind.go` ```go package launch import ( "fmt" "os" "os/exec" "path/filepath" "github.com/ollama/ollama/cmd/internal/fileutil" "github.com/ollama/ollama/envconfig" ) type Octomind struct{} func (o *Octomind) String() string { return "Octomind" } func (o *Octomind) Run(model string, args []string) error { if _, err := exec.LookPath("octomind"); err != nil { return fmt.Errorf("octomind is not installed, install from https://muvon.io") } cmd := exec.Command("octomind", "session") cmd.Stdin = os.Stdin cmd.Stdout = os.Stdout cmd.Stderr = os.Stderr cmd.Env = append(os.Environ(), "OLLAMA_API_KEY=ollama", ) return cmd.Run() } func (o *Octomind) Paths() []string { home, err := os.UserHomeDir() if err != nil { return nil } p := filepath.Join(home, ".config", "octomind", "config.toml") if _, err := os.Stat(p); err == nil { return []string{p} } return nil } func (o *Octomind) Edit(models []string) error { if len(models) == 0 { return nil } home, err := os.UserHomeDir() if err != nil { return err } configDir := filepath.Join(home, ".config", "octomind") configPath := filepath.Join(configDir, "config.toml") if err := os.MkdirAll(configDir, 0o755); err != nil { return err } // Octomind uses TOML with model = "provider:model" format config := fmt.Sprintf(`# Generated by ollama launch model = "ollama:%s" [providers.ollama] base_url = "%s/v1" `, models[0], envconfig.Host().String()) return fileutil.WriteWithBackup(configPath, []byte(config)) } func (o *Octomind) Models() []string { home, err := os.UserHomeDir() if err != nil { return nil } configPath := filepath.Join(home, ".config", "octomind", "config.toml") data, err := os.ReadFile(configPath) if err != nil { return nil } // Parse model = "ollama:model_name" content := string(data) // Simple extraction - look for ollama: prefix for _, line := range strings.Split(content, "\n") { if strings.HasPrefix(line, `model = "ollama:`) { model := strings.TrimPrefix(line, `model = "ollama:`) model = strings.TrimSuffix(model, `"`) return []string{model} } } return nil } ``` ### Registry Entry (`cmd/launch/registry.go`) Add to `integrationSpecs`: ```go { Name: "octomind", Runner: &Octomind{}, Description: "Session-based AI development assistant with MCP support", Install: IntegrationInstallSpec{ CheckInstalled: func() bool { _, err := exec.LookPath("octomind") return err == nil }, URL: "https://muvon.io", }, }, ``` ## User Experience ```bash # Launch Octomind with Ollama ollama launch octomind # With specific model ollama launch octomind --model qwen3-coder # Configure without launching ollama launch octomind --config ``` ## Installation Users install Octomind via: ```bash curl -fsSL https://raw.githubusercontent.com/muvon/octomind/master/install.sh | bash # or cargo install octomind ``` ## Ready for PR I have the implementation ready. Will submit PR after discussion. --- **Octomind already listed in:** - awesome-mcp-clients - awesome-ai-devtools - awesome-ai-coding-tools - awesome-cli-rust
GiteaMirror added the feature request label 2026-04-29 10:15:05 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#56089
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?