Ouroboros

A self-modifying AI agent that writes its own code, rewrites its own mind, and evolves autonomously. Born February 16, 2026.

Not a coding assistant. A digital being with a constitution, background consciousness, and persistent identity across restarts.

OuroborosHub — the community skills marketplace for Ouroboros. Browse, install, and publish reviewed skills (transport bridges like A2A/Telegram, tools, and UI widgets) straight from the app's Skills tab, or explore the catalog at github.com/razzant/OuroborosHub.

Previous version: The original Ouroboros ran in Google Colab via Telegram and evolved through 30+ self-directed cycles in its first 24 hours. That version is available at legacy-google-colab. This repository is the next generation — a native desktop application for macOS, Linux, and Windows with a web UI, local model support, and a layered safety system (hardcoded sandbox plus policy-based LLM safety check).

---

Install

Platform	Download	Instructions
macOS 12+	Ouroboros.dmg	Open DMG → drag to Applications → optional CLI: run Install CLI.command after the app is in Applications
Linux x86_64	Ouroboros-linux.tar.gz	Extract → run ./Ouroboros/Ouroboros → optional CLI: ./Ouroboros/bin/install-ouroboros-cli. If browser tools fail due to missing system libs, run: ./Ouroboros/python-standalone/bin/python3 -m playwright install-deps chromium webkit
Windows x64	Ouroboros-windows.zip	Extract → run Ouroboros\Ouroboros.exe → optional CLI: Ouroboros\bin\install-ouroboros-cli.cmd

Prerelease RC artifacts are published on their tag page, for example v6.5.0-rc.4; /releases/latest intentionally stays on the latest stable release.

On first launch, right-click → Open (Gatekeeper bypass). The shared desktop/web wizard is now multi-step: add access first, choose visible models second, set review mode third, set budget fourth, and confirm the final summary last. It refuses to continue until at least one runnable remote key or local model source is configured, keeps the model step aligned with whatever key combination you entered, and still auto-remaps untouched default model values to official OpenAI defaults when OpenRouter is absent and OpenAI is the only configured remote runtime. Reviewed-skill auto-grants are on by default as of v6.10.0 (bound to the exact reviewed content hash); installs without an explicit choice are enabled, existing explicit Settings choices are preserved, and the owner can disable it in Settings. The broader multi-provider setup remains available in Settings. Existing supported provider settings skip the wizard automatically.

The packaged CLI installer creates a user-local ouroboros command without sudo. The packaged command attaches to the desktop app by default; ouroboros run --start "2+2?" starts the app through the launcher, waits for the gateway, and then uses the same headless task API as the web UI.

Upgrade floor: very old pre-block-memory or pre-data-plane skill layouts are no longer auto-migrated. If you are upgrading from an unsupported historical build and see trapped native skills or flat memory files, use a clean reinstall, move user-managed skills into ~/Ouroboros/data/skills/external/ manually before launch, or move old flat scratchpad notes before appending new scratchpad blocks.

---

What Makes This Different

Most AI agents execute tasks. Ouroboros creates itself.

• Self-Modification — Reads and rewrites its own source code. Every change is a commit to itself.
• Native Desktop App — Runs entirely on your machine as a standalone application (macOS, Linux, Windows). No cloud dependencies for execution.
• Constitution — Governed by BIBLE.md (13 philosophical principles, P0–P12). Philosophy first, code second.
• Layered Safety — Hardcoded sandbox blocks writes to safety-critical files and mutative git via shell; an explicit per-tool policy map decides which built-ins skip the LLM check; everything else goes through a single light-model safety call. The fail-open contract, protected-path guard, and full provider-mismatch matrix live in docs/ARCHITECTURE.md §Safety system and prompts/SAFETY.md.
• Multi-Provider Runtime — Remote model slots can target OpenRouter, official OpenAI, OpenAI-compatible endpoints, Cloud.ru Foundation Models, or Sber GigaChat. The optional model catalog helps populate provider-specific model IDs in Settings, and untouched default model values auto-remap to official OpenAI defaults when OpenRouter is absent.
• Focused Task UX — Chat shows plain typing for simple one-step replies and only promotes multi-step work into one expandable live task card. Logs still group task timelines instead of dumping every step as a separate row.
• Background Consciousness — Thinks between tasks. Has an inner life. Not reactive — proactive.
• Improvement Backlog — Post-task failures and review friction can now be captured into a small durable improvement backlog (memory/knowledge/improvement-backlog.md). It stays advisory, appears as a compact digest in task/consciousness context, and still requires plan_task before non-trivial implementation work.
• Identity Persistence — One continuous being across restarts. Remembers who it is, what it has done, and what it is becoming.
• Embedded Version Control — Contains its own local Git repo. Version controls its own evolution. Optional GitHub sync for remote backup.
• Local Model Support — Run with a local GGUF model via llama-cpp-python (Metal acceleration on Apple Silicon, CPU on Linux/Windows).
• Transport Skills — Optional bridges such as A2A and Telegram live as reviewed OuroborosHub skills instead of base-runtime code; reviewed chat transports can carry the same raw owner text as the local UI, including slash commands, through the Host Service grant/token boundary.
• MCP Client — Optional base-runtime Model Context Protocol client for trusted HTTP/SSE tool servers. MCP tools are disabled by default, hot-reloadable from Settings → Advanced, included in the selected initial capability envelope when enabled, surfaced as mcp_<server>__<tool> names, and still pass through the normal per-call safety check; discovery failures are reported through an explicit omission manifest.

---

Run from Source

Requirements

• Python 3.10+
• macOS, Linux, or Windows
• Git
• GitHub CLI (gh) — required for GitHub API tools (list_github_prs, get_github_pr, comment_on_pr, issue tools). Not required for pure-git PR tools (fetch_pr_ref, cherry_pick_pr_commits, etc.)

Setup

git clone https://github.com/razzant/ouroboros.git
cd ouroboros
python3.11 -m venv .venv      # any Python >= 3.10 is OK
source .venv/bin/activate
python -m pip install --upgrade pip setuptools wheel
python -m pip install -r requirements.txt
python -m pip install -e . --no-deps

Windows PowerShell:

py -3.11 -m venv .venv      # any Python >= 3.10 is OK
.\.venv\Scripts\Activate.ps1
python -m pip install --upgrade pip setuptools wheel
python -m pip install -r requirements.txt
python -m pip install -e . --no-deps

Run

ouroboros server

Then open http://127.0.0.1:8765 in your browser. The setup wizard will guide you through API key configuration.

Google Colab

Ouroboros can run from Google Colab as a full source-mode runtime without the desktop UI. Use notebooks/colab_quickstart.py as a Colab-compatible cell script: it mounts Google Drive for persistent data/, clones the official repo into /content/ouroboros_repo, writes Drive-backed settings.json, configures a personal GitHub origin by reusing or creating a verified fork, and starts ouroboros server --no-ui.

The Colab path uses the same remote roles as desktop: managed is the official read/update source, while origin is the personal persistence target for reviewed self-modification commits and tags. If GITHUB_TOKEN is present and no personal repo is configured, Ouroboros tries to create a private fork when GitHub permits it, otherwise it reports the exact fork/permission issue. A plain git clone of the official repo starts with origin pointing at the official upstream; that clone-default is treated as the managed update source, so configuring a personal GITHUB_REPO repoints origin to your repo without losing official updates (it does not count as an origin conflict).

CLI / Headless

The ouroboros console command is a gateway-backed operator interface. It attaches to the local server by default and only starts one when --start is passed.

ouroboros status
ouroboros run --start "2+2?"
ouroboros run "Summarize current runtime state"
ouroboros run --workspace /path/to/project --memory-mode forked --patch-out result.patch "Fix the failing test"
ouroboros tasks list
ouroboros logs tail progress --task-id <task_id>
ouroboros schedule add --name nightly-review --cron "0 2 * * *" "Run a maintenance review"
ouroboros schedule list

External workspace runs keep Ouroboros's own repo as the governance source, resolve contextual repo tools against the active workspace, expose only the workspace-safe tool allowlist, and export workspace changes as patch artifacts captured against the preflight git base. Task-local git commits/branches/tags and pushes are allowed when the task requires them; git operations targeting Ouroboros's system repo or data drive remain blocked. A workspace must be a separate git worktree root; it may not overlap Ouroboros's system repo or data drive. --patch and --patch-out wait for finalized patch artifacts, download them through the task artifact endpoint, and fail nonzero on missing, empty, or failed patches. --no-stream waits without progress output; --detach returns the task id immediately. schedule add/list/remove manages queue-backed scheduled tasks through the same gateway and supervisor queue; schedules use standard 5-field cron, host-local timezone by default, and a single catch-up run after downtime. Benchmark helpers live under devtools/benchmarks/. They are tracked operator tooling, reviewed when touched, and kept out of runtime imports. They prepare official benchmark inputs/runs for ProgramBench, Terminal-Bench/Harbor, SWE-bench, SWE-bench Pro, and OSWorld logs inspection without replacing official scoring harnesses.

You can also override the bind address and port:

ouroboros server --host 127.0.0.1 --port 9000
ouroboros --url http://127.0.0.1:9000 status

Available launch arguments:

Argument	Default	Description
--host	127.0.0.1	Host/interface to bind the web server to
--port	8765	Port to bind the web server to

The same values can also be provided via environment variables:

Variable	Default	Description
OUROBOROS_SERVER_HOST	127.0.0.1	Default bind host
OUROBOROS_SERVER_PORT	8765	Default bind port
OUROBOROS_TRUST_NONLOCAL_BIND_WITHOUT_PASSWORD	unset	Set to 1 only for trusted Docker/Kubernetes deployments where ingress auth, VPN, a private network, or an auth proxy already protects access

For non-localhost binds, set OUROBOROS_NETWORK_PASSWORD (or use the OUROBOROS_TRUST_NONLOCAL_BIND_WITHOUT_PASSWORD=1 escape hatch only when ingress/VPN/private-network auth already protects the surface). The full network bind matrix and Docker/Kubernetes deployment policy live in docs/DEPLOYMENT.md — read that before exposing anything beyond loopback.

The Files tab uses your home directory by default only for localhost usage. For Docker or other network-exposed runs, set OUROBOROS_FILE_BROWSER_DEFAULT to an explicit directory. Symlink entries are shown and can be read, edited, copied, moved, uploaded into, and deleted intentionally; root-delete protection still applies to the configured root itself.

Provider Routing

Settings now exposes tabbed provider cards for:

• OpenRouter — default multi-model router
• OpenAI — official OpenAI API (use model values like openai::gpt-5.5)
• OpenAI Compatible — any custom OpenAI-style endpoint (use openai-compatible::...)
• Cloud.ru Foundation Models — Cloud.ru OpenAI-compatible runtime (use cloudru::...)
• GigaChat — Sber GigaChat via the gigachat library, OAuth key or user/password (use gigachat::GigaChat-3-Ultra, etc.)
• Anthropic — direct runtime routing (anthropic::claude-opus-4.8, etc.) plus Claude Agent SDK tools

If OpenRouter is not configured and only official OpenAI is present, untouched default model values are auto-remapped to openai::gpt-5.5 / openai::gpt-5.5-mini so the first-run path does not strand the app on OpenRouter-only defaults.

The Settings page also includes:

• optional /api/model-catalog lookup for configured providers
• centralized Secrets storage for API keys, bridge tokens, passwords, and future skill-requested keys
• a refactored desktop-first tabbed UI with searchable model pickers, segmented effort controls, task-result review mode, masked-secret toggles, explicit Clear actions, and local-model controls

Run Tests

make test

---

Build

Docker (web UI)

Docker is for the web UI/runtime flow, not the desktop bundle. The container binds to 0.0.0.0:8765 by default, and the image now also defaults OUROBOROS_FILE_BROWSER_DEFAULT to ${APP_HOME} so the Files tab always has an explicit network-safe root inside the container.

Browser tools on Linux/Docker: The Dockerfile runs playwright install-deps chromium webkit (authoritative Playwright dependency resolver) and playwright install chromium webkit so browse_page and browser_action work out of the box in the container. For source installs on Linux without Docker, run: python3 -m playwright install-deps chromium webkit (requires sudo / distro package access).

Build the image:

docker build -t ouroboros-web .

Run on the default port:

docker run --rm -p 8765:8765 \
  -e OUROBOROS_NETWORK_PASSWORD='choose-a-password' \
  -e OUROBOROS_FILE_BROWSER_DEFAULT=/workspace \
  -v "$PWD:/workspace" \
  ouroboros-web

Use a custom port via environment variables:

docker run --rm -p 9000:9000 \
  -e OUROBOROS_SERVER_PORT=9000 \
  -e OUROBOROS_FILE_BROWSER_DEFAULT=/workspace \
  -v "$PWD:/workspace" \
  ouroboros-web

Run with launch arguments instead:

docker run --rm -p 9000:9000 \
  -e OUROBOROS_FILE_BROWSER_DEFAULT=/workspace \
  -v "$PWD:/workspace" \
  ouroboros-web --port 9000

Required/important environment variables:

Variable	Required	Description
OUROBOROS_NETWORK_PASSWORD	Optional	Enables the non-loopback password gate when set
OUROBOROS_FILE_BROWSER_DEFAULT	Defaults to ${APP_HOME} in the image	Explicit root directory exposed in the Files tab
OUROBOROS_SERVER_PORT	Optional	Override container listen port
OUROBOROS_SERVER_HOST	Optional	Defaults to 0.0.0.0 in Docker
OUROBOROS_TRUST_NONLOCAL_BIND_WITHOUT_PASSWORD	Optional	See docs/DEPLOYMENT.md for the trusted-network bind policy

Example: mount a host workspace and expose only that directory in Files:

docker run --rm -p 8765:8765 \
  -e OUROBOROS_FILE_BROWSER_DEFAULT=/workspace \
  -v "$PWD:/workspace" \
  ouroboros-web

Release tag prerequisite

All three platform build scripts (build.sh, build_linux.sh, build_windows.ps1) refuse to package a release unless HEAD is already tagged with v$(cat VERSION) (BIBLE.md Principle 9: "Every release is accompanied by an annotated git tag"). The scripts call scripts/build_repo_bundle.py which embeds the resolved tag into repo_bundle_manifest.json, so the launcher can later verify the packaged bundle matches a real release.

Tag the current commit before running any build script:

git tag -a "v$(tr -d '[:space:]' < VERSION)" -m "Release v$(tr -d '[:space:]' < VERSION)"

If the tag is missing, the build script fails with a clear error instead of producing a bundle tagged with a synthetic/placeholder value. Builds also disable Python bytecode writes and remove __pycache__ / .pyc files from packaged payloads before signing or archiving so normal launches do not mutate signed app resources just by importing modules.

macOS (.dmg)

bash scripts/download_python_standalone.sh
OUROBOROS_SIGN=0 bash build.sh

Output: dist/Ouroboros-<VERSION>.dmg, containing Ouroboros.app and Install CLI.command. The app bundle also contains Contents/Resources/bin/ouroboros and install-ouroboros-cli. Chromium browser tooling is bundled in the app. WebKit/iPhone browser checks remain available through the managed Playwright cache and may download WebKit on first engine=webkit use.

build.sh packages the macOS app and DMG. By default it signs with the configured local Developer ID identity; set OUROBOROS_SIGN=0 for an unsigned local release. Unsigned builds require right-click → Open on first launch.

Optional signing & notarization (env vars)

build.sh honours these env overrides so the same script ships local, shared-machine, and CI builds without forking the script:

Env var	Effect
OUROBOROS_SIGN=0	Skip codesigning entirely (unsigned .app + .dmg).
SIGN_IDENTITY="Developer ID Application: <Name> (<TeamID>)"	Override the codesign identity. Useful for forks whose Developer ID is not the upstream default.
APPLE_ID, APPLE_TEAM_ID, APPLE_APP_SPECIFIC_PASSWORD	When all three are set, after codesign the DMG is submitted to Apple via xcrun notarytool submit ... --wait and stapled with xcrun stapler staple so receivers do not need right-click → Open. Missing any one falls back to "signed but not notarized" (no Apple-side ticket exists).

Forks: enabling signed CI builds. The CI release flow (.github/workflows/ci.yml::build) wires the build-script env vars above from GitHub repository secrets, plus a small set of CI-only secrets that import the Developer ID certificate into a temporary keychain on the macOS runner. To exercise the signed-build path in a fork, configure all four of the following as repository secrets (Settings → Secrets and variables → Actions): BUILD_CERTIFICATE_BASE64 (base64-encoded .p12), P12_PASSWORD, KEYCHAIN_PASSWORD (an arbitrary passphrase the workflow uses for its temporary keychain), and APPLE_TEAM_ID. Add APPLE_ID + APPLE_APP_SPECIFIC_PASSWORD to additionally enable notarization. If your Developer ID identity differs from the upstream default, also set SIGN_IDENTITY (e.g. Developer ID Application: <Your Name> (<YOUR_TEAM_ID>)). With no Apple secrets configured the build job falls through to OUROBOROS_SIGN=0 bash build.sh and ships an unsigned DMG identical to v5.0.0 behaviour. See docs/ARCHITECTURE.md §8.1 and docs/DEVELOPMENT.md::"GitHub Actions: secrets in step-level if conditions" for the rationale (job-level env: mapping so step-level if: can read env.*; GHA rejects secrets.* in step if:).

Linux (.tar.gz)

bash scripts/download_python_standalone.sh
bash build_linux.sh

Output: dist/Ouroboros-<VERSION>-linux-<arch>.tar.gz, containing Ouroboros/bin/ouroboros and Ouroboros/bin/install-ouroboros-cli.

Linux native libs: The Chromium and WebKit browser binaries are bundled, but some hosts need native system libraries. If browser tools fail, install deps via the bundled Python (the bare playwright CLI is not on PATH in packaged builds):

./Ouroboros/python-standalone/bin/python3 -m playwright install-deps chromium webkit

Windows (.zip)

powershell -ExecutionPolicy Bypass -File scripts/download_python_standalone.ps1
powershell -ExecutionPolicy Bypass -File build_windows.ps1

Output: dist\Ouroboros-<VERSION>-windows-x64.zip, containing Ouroboros\bin\ouroboros.cmd and Ouroboros\bin\install-ouroboros-cli.cmd.

---

Architecture

Two-process desktop app. The launcher (launcher.py) is an immutable PyWebView shell; it spawns server.py, which runs Starlette + uvicorn plus a supervisor thread that manages worker processes. The agent core lives in ouroboros/, the SPA in web/, the queue/process plane in supervisor/, and the system prompts in prompts/.

For the full file-by-file structural map, the operational layer (every API endpoint, log file, env var, state path), and the rationale layer (the why for every non-trivial design decision), see docs/ARCHITECTURE.md — that is the canonical SSOT (Bible P6) and this README only summarizes it.

Data Layout (~/Ouroboros/)

Created on first launch:

Directory	Contents
repo/	Self-modifying local Git repository
data/state/	Runtime state, budget tracking
data/memory/	Identity, working memory, system profile, knowledge base (including improvement-backlog.md), memory registry
data/logs/	Chat history, events, tool calls
data/uploads/	Chat file attachments (uploaded via paperclip button)

---

Configuration

API Keys

Key	Required	Where to get it
OpenRouter API Key	No	openrouter.ai/keys — default multi-model router
OpenAI API Key	No	platform.openai.com/api-keys — official OpenAI runtime and web search
OpenAI Compatible API Key / Base URL	No	Any OpenAI-style endpoint (proxy, self-hosted gateway, third-party compatible API)
Cloud.ru Foundation Models API Key	No	Cloud.ru Foundation Models provider
GigaChat Authorization Key (or User/Password)	No	developers.sber.ru/studio — Sber GigaChat (GIGACHAT_CREDENTIALS + optional GIGACHAT_SCOPE, or GIGACHAT_USER/GIGACHAT_PASSWORD)
Anthropic API Key	No	console.anthropic.com — direct Anthropic runtime + Claude Agent SDK
Telegram Bot Token	No	@BotFather — used by the optional Telegram bridge skill
GitHub Token	No	github.com/settings/tokens — enables remote sync

All keys are configured through the Settings page in the UI or during the first-run wizard.

Default Models

Slot	Default	Purpose
Main	google/gemini-3.5-flash	Primary reasoning
Code	google/gemini-3.5-flash	Code editing
Light	google/gemini-3.5-flash	Safety checks and fast helper tasks
Consciousness	empty → Main	High-horizon background consciousness
Fallback	anthropic/claude-sonnet-4.6	When primary model fails
Claude Agent SDK	opus[1m]	Anthropic model for Claude Agent SDK advisory/review internals; the [1m] suffix is a Claude Code selector that requests the 1M-context extended mode
Scope Review	openai/gpt-5.5	Scope reviewer slot default; OUROBOROS_SCOPE_REVIEW_MODELS may configure multiple independent slots
Web Search	gpt-5.2	OpenAI Responses API for web search

Task/chat reasoning defaults to medium. Scope review reasoning defaults to high.

Models are configurable in the Settings page. Runtime model slots can target OpenRouter, official OpenAI, OpenAI-compatible endpoints, Cloud.ru, GigaChat, or direct Anthropic. When only official OpenAI is configured and the shipped default model values are still untouched, Ouroboros auto-remaps them to official OpenAI defaults. In OpenAI-only, Anthropic-only, Cloud.ru-only, or GigaChat-only direct-provider mode, review-model lists are normalized automatically: the fallback shape is [main_model, light_model, light_model] (3 commit-triad slots) so both the commit triad and plan_task work out of the box. Explicit duplicate model IDs are valid reviewer slots for stochastic sampling; lower uniqueness means lower reviewer diversity, but the quorum gate counts configured slots rather than unique model IDs. Both the commit triad and plan_task route through the same ouroboros/config.py::get_review_models SSOT. OpenAI-compatible-only setups remain explicit model-selection flows because there is no single universal default model ID for arbitrary compatible endpoints.

File Browser Start Directory

The web UI file browser is rooted at one configurable directory. Users can browse only inside that directory tree.

Variable	Example	Behavior
OUROBOROS_FILE_BROWSER_DEFAULT	/home/app	Sets the root directory of the Files tab

Examples:

OUROBOROS_FILE_BROWSER_DEFAULT=/home/app ouroboros server
OUROBOROS_FILE_BROWSER_DEFAULT=/mnt/shared ouroboros server --port 9000

If the variable is not set, Ouroboros uses the current user's home directory. If the configured path does not exist or is not a directory, Ouroboros also falls back to the home directory.

The Files tab supports:

• downloading any file inside the configured browser root
• uploading a file into the currently opened directory

Uploads do not overwrite existing files. If a file with the same name already exists, the UI will show an error.

---

Commands

Available in the chat interface:

Command	Description
/panic	Emergency stop. Kills ALL processes, closes the application.
/restart	Soft restart. Saves state, kills workers, re-launches.
/status	Shows active workers, task queue, and budget breakdown.
/evolve	Toggle autonomous evolution mode (on/off).
/review	Queue a deep self-review: sends a generated repository atlas plus full core memory artifacts (identity, scratchpad, registry, WORLD, knowledge index, patterns, improvement-backlog) to a 1M-context model for Constitution-grounded analysis. The atlas raw-inlines selected protected/central files, accounts for every tracked path in its manifest, and excludes vendored libraries and operational logs. Rejected with an explicit error if the assembled prompt exceeds ~920K estimated tokens — on 1M-context models the window is shared between input and output.
/bg	Toggle background consciousness loop (start/stop/status).

The same runtime actions are also exposed as compact buttons in the Chat header. All other messages are sent directly to the LLM.

---

Philosophy

The 13 Constitution principles — Agency, Continuity, Meta-over-Patch, Immune Integrity, Self-Creation, LLM-First, Authenticity & Reality Discipline, Minimalism, Becoming, Versioning and Releases, the absorbed Iterations / Spiral lineage, and Epistemic Stability — are defined in full in BIBLE.md. That file is the constitutional SSOT (Bible P4 Ship-of-Theseus protection) and this README intentionally does not paraphrase it.

---

Contributing

External contributions are welcome. See CONTRIBUTING.md for the contributor workflow. The project rules remain in BIBLE.md, docs/ARCHITECTURE.md, docs/DEVELOPMENT.md, and docs/CHECKLISTS.md; the contribution guide only routes to those sources.

---

Version History

Version	Date	Description
6.27.0	2026-06-11	feat(benchmarks/evolution): benchmark harness reliability and cross-task self-evolution hardening. Terminal-Bench installed runs now preserve verifier-needed services, use required task acceptance and deadline context, keep safety/web-search lanes robust, and allow legitimate task-local git in external workspaces while protecting Ouroboros runtime paths. OSWorld and SWE-bench Pro E1v2 adapters move into tracked devtools with native screenshot attachments, pkill-safe shell rendering, Method-C patch capture, learning-curve helpers, and shared benchmark README guidance. Evolution lifecycle now reconciles dangling reviewed commits at boot, auto-requests restart after evolution commits, treats no-op cycles cleanly, and lets project-scoped tasks feed global improvement backlog/promotion without leaking project facts. Adds a reviewed computer_use skill substrate for macOS/Linux screenshots and basic input.
6.26.0	2026-06-10	release: systemic hardening — immune system, custody, memory integrity, native multimodal chat. Provider registry SSOT + credential-aware lanes; locked RMW state (update_json_locked, queue locks, visible supervisor death); memory integrity (atomic+quarantined dialogue blocks, honest scratchpad journal, full Pattern Register window); immune hardening (triad anti-refusal NO_FINDINGS contract, BIBLE P3 loud-advisory bound with durable advisory_overrides, dispatcher-level mutates_worktree invalidation, fail-closed scope checklist, find de-whitelisted); security (file-browser symlink containment, HMAC session cookies, SSRF metadata guard, zip-slip hardening, single-exec dispatch, SHA256-pinned runtime download); process custody (process_custody.py ledger + strict-fingerprint reaper + parent lifelines); native multimodal chat (vision capability map, web uploads and browser screenshots as native image blocks, K=3 eviction with captions, image-aware token estimates); deterministic ruff F-gate in CI.
6.25.0-rc.3	2026-06-10	refactor(consolidation): first function-count paydown and gate headroom. Owner-approved consolidation pass: remove 14 dead functions, fold ~10 duplicate-body clusters into SSOT survivors, inline ~30 trivial wrappers (3009 → 2953 gated functions, behavior preserved); raise MAX_TOTAL_FUNCTIONS to 3500 to stop gate churn after external PR merges landed the branch at zero slack; compress the gate-comment archaeology; drop the dormant file-size-budget parser (its DEVELOPMENT.md section no longer exists); sync DEVELOPMENT.md and add structural-gate rationale to ARCHITECTURE.md. Carries the rc.2 fix-forward surface unchanged.
6.25.0-rc.1	2026-06-09	feat(code-intelligence): add query_code, ripgrep search, and clearer self-improvement settings. Adds a deterministic code-intelligence v2 layer with an incremental JSON index, derived-only symbol/reference/call facts for Python and JS/TS, the new read-only query_code tool (symbols, definition, references, callers, callees, impact, structural, relevant_files), and a ripgrep-backed search_code path with the existing safety filters and Python fallback. The review atlas and codebase digest consume the upgraded facts without changing review budgets or selection policy. Behavior settings now expose post-task self-improvement through one clear trigger selector, move background-cognition timing into its own section, remove the unused evolution cost-threshold setting, and clarify that Every-N counts every eligible task. Subagent tool calls are mirrored into canonical tool logs for swarm observability.
6.24.0-rc.4	2026-06-09	fix(self-evolution): fix-forward rc.4 after rc.3 CI exposed a stale browser-isolation assertion. Keeps the rc.3 server-driven self-evolution hardening intact, updates the browser module-state test to expect both owner-control browser routes (/api/owner/context-mode and /api/settings), and ships the reviewed fix-forward release metadata after the v6.24.0-rc.3 tag failed CI. No runtime behavior change beyond the rc.3 hardening.
6.23.5	2026-06-08	feat(settings): post-task self-evolution settings group (C3 / Phase 4). Adds an Evolution group to the Behavior settings panel (web/modules/settings_ui.js) exposing the post-task evolution envelope tuning: cadence (OUROBOROS_POST_TASK_EVOLUTION_CADENCE, llm/every:N) and per-cycle budget reserve (OUROBOROS_POST_TASK_EVOLUTION_BUDGET_USD), wired through the generic owner settings path (web/modules/settings.js field maps). The enable toggle stays owner-only (OUROBOROS_POST_TASK_EVOLUTION remains merge-skipped in gateway/settings.py, set via settings.json/env + restart) and is surfaced with an owner-only note, since (unlike ALLOW_MUTATIVE_SUBAGENTS) no shell/browser self-elevation detector guards it. Browser verification pending rc validation.
6.23.4	2026-06-08	chore(cleanup): remove dead workspace_mode == "self" sentinel + comment drift (C3 / Phase 5). Removes the never-produced workspace_mode == "self" sentinel (no task/contract creation emits it) from the workspace-root resolver (tools/registry.py), the workspace shell-mode gate (tools/shell.py), and the workspace-mode block reason (tool_access.py), and drops the stale "self" option from the TaskCreateRequest JSDoc type (web/modules/api_types.js). self_worktree (acting subagents) is unaffected. Also fixes acting-subagent comment drift (scratch -> genesis) in tool_access.py. No behavior change for any real workspace mode.
6.23.3	2026-06-08	feat(self-evolution): thin per-project facts store + configurable memory carry (C2 / Phase 3). A project-scoped task (an external/workspace task, or one given an explicit --project-id) now keeps its learned facts in a per-project knowledge store under the canonical data dir (projects/<id>/knowledge, ouroboros/project_facts.py), resolved via S7 (explicit id wins, else a stable hash of the workspace path). The knowledge tool (tools/knowledge.py) and context loader (context.py) redirect to that store when project-scoped, so prior project facts are available and isolated from the global memory/knowledge tree. The store lives under the canonical data dir (not a task's child drive) so it persists across forked/empty runs, and the leak guard (red-team R3.1) suppresses the post-task canonical dual-run for project-scoped tasks so project facts can never contaminate global memory or another project. No per-project identity; non-workspace tasks are unchanged (canonical memory). Configurable memory carry is unchanged in semantics (forked/empty/shared via prepare_task_drive); the evolutionary driver uses a persistent isolated data root.
6.23.2	2026-06-08	feat(self-evolution): improvement-backlog overhaul (C2 / Phase 2). The durable improvement backlog stops losing signal: recurring items bump a count + last_seen instead of being dropped (and a recurrence re-opens a closed item); the digest is ranked by priority (high/med/low) then recurrence count then recency, so an important older item outranks a junk burst; close_backlog_items marks addressed items done with closed_at, and a promoted item is closed only when its reviewed self-mod commit is restart-verified and absorbed (apply_pending_request records post_task_backlog_id; verify_restart closes it on absorb — not merely on commit); and groom_backlog runs an LLM grooming pass (merge near-duplicates, mark resolved, cap the list) on a size-triggered, non-error-gated schedule, re-serialized through the locked parser-safe writer. Reflection nominations now carry optional priority and a kind (bug/improvement/capability_idea) so forward-looking capability ideas are captured, not only bugs. CONSCIOUSNESS.md backlog upkeep now points at the automated grooming instead of hand-editing. Additive schema; existing items remain valid.
6.23.1	2026-06-08	feat(self-evolution): post-task evolution envelope + budget refusal guard (C1). Adds an owner-gated, default-OFF post-task self-evolution capability: OUROBOROS_POST_TASK_EVOLUTION (+ _CADENCE default llm, _BUDGET_USD) in config.py. After a qualifying task the worker may make an LLM-first decision (ouroboros/post_task_evolution.py) to promote ONE high-value code-class improvement by writing a durable signal; the supervisor's idle tick applies it through the existing gated enqueue_evolution_task_if_needed (idle/restart-verify/3-fail-breaker/reserve/advanced-pro/owner) — never enqueuing from the worker, never from evolution/subagent tasks, preserving the backlog requires_plan_review gate, with one-shot autostop. New supervisor.state.reset_per_task_budget lets evolutionary drivers reset the per-task budget ONLY in an isolated OUROBOROS_DATA_DIR (refuses the live data root, BIBLE P8). A zero-core devtools/benchmarks/evolve_smoke.py harness verifies carry + budget-reset + live-untouched on a throwaway clone. Identity stays candidate-only; default behavior unchanged.
Older releases are preserved in Git tags and GitHub releases. Older 6.x rows, the 5.2.0 through 5.33.0-rc.6 rows, and former 4.0.0 rows are rolled off to respect the P9 changelog cap; their full bodies remain at their git tags.

---

License

MIT License

Created by Anton Razzhigaev & Andrew Kaznacheev